Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional states and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Japanese particles (にも, すら, だと, でも, が, に)

    np_acts-logits-general · gemini-2.0-flash

    Japanese particles and function words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    続きます
    -0.48
    ıyoruz
    -0.47
    を受けた
    -0.46
    こない
    -0.46
    違います
    -0.45
    mişti
    -0.44
    ıyordu
    -0.44
    ktı
    -0.43
    pisah
    -0.43
    ıyors
    -0.43
    POSITIVE LOGITS
     MainAxisSize
    0.93
    躇
    0.83
    WebVitals
    0.82
    onViewCreated
    0.82
    AnchorStyles
    0.81
    PYX
    0.81
     gynhyrchwyd
    0.81
    ArgsConstructor
    0.79
    Hentet
    0.79
    ArrowToggle
    0.78
    Act Density 0.088%

    No Known Activations