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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user-oriented devices and their functionalities

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

    Followed by a verb of requirement/desire

    np_acts-logits-general · gemini-2.0-flash

    who needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gelungen
    -0.37
    titleMargin
    -0.36
    gms
    -0.33
    ちゃんと
    -0.33
    principalTable
    -0.33
    jdt
    -0.31
    arim
    -0.30
    JsonInclude
    -0.29
    rung
    -0.28
    macy
    -0.28
    POSITIVE LOGITS
     needs
    1.52
     needing
    1.46
     need
    1.46
    needs
    1.34
     Needs
    1.34
    Need
    1.31
     Need
    1.30
    need
    1.30
    Needs
    1.23
    需要
    1.23
    Act Density 0.857%

    No Known Activations