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

    Neuronpedia

    INDEX
    Explanations

    phrases related to processes, actions, and outcomes

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

    verbs describing actions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.63
     ImportError
    -0.57
     iſt
    -0.57
     LOGGER
    -0.56
    iſh
    -0.55
     purpoſe
    -0.52
    rlpool
    -0.52
     adel
    -0.52
    ELTS
    -0.51
     neer
    -0.51
    POSITIVE LOGITS
     mukana
    0.40
     palvel
    0.39
     kiin
    0.39
     kysy
    0.38
     käyt
    0.37
     Chwiliwch
    0.37
     yrity
    0.37
    ValueGenerated
    0.37
     löytyy
    0.37
     lisäksi
    0.35
    Act Density 0.275%

    No Known Activations