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

    Neuronpedia

    INDEX
    Explanations

    "in addition to" or "in place of"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ξ
    -0.08
    AttributeName
    -0.07
     wegen
    -0.07
    olg
    -0.07
    出局
    -0.07
    .column
    -0.07
    ولد
    -0.07
    玩家来说
    -0.07
     radians
    -0.07
    心跳
    -0.07
    POSITIVE LOGITS
     clarification
    0.07
    之前
    0.06
     stripslashes
    0.06
    _MY
    0.06
    istique
    0.06
     targeted
    0.06
    👆
    0.06
    scri
    0.06
     конкрет
    0.06
     Chronicle
    0.06
    Act Density 0.035%

    No Known Activations