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

    Neuronpedia

    INDEX
    Explanations

    Connecting or joining things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mieux
    -0.07
     Somebody
    -0.07
     obedience
    -0.07
    101
    -0.07
     republic
    -0.07
    Everyone
    -0.06
    -producing
    -0.06
     Origin
    -0.06
    _SELF
    -0.06
    ziel
    -0.06
    POSITIVE LOGITS
     goalt
    0.07
     สร
    0.06
    无码
    0.06
    .Ph
    0.06
    寶
    0.06
     ген
    0.06
    änder
    0.06
    ประเภท
    0.06
     heatmap
    0.06
    ươ
    0.06
    Act Density 0.168%

    No Known Activations