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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    insula
    -0.06
    意大
    -0.06
    .simpleButton
    -0.06
     ascend
    -0.06
    pósito
    -0.06
     ス
    -0.06
     stripes
    -0.06
     creature
    -0.06
     Bed
    -0.06
     attempt
    -0.06
    POSITIVE LOGITS
    Owned
    0.08
     defamation
    0.07
    妻
    0.07
    	LP
    0.07
    /man
    0.07
     ניה
    0.06
    源
    0.06
    TableModel
    0.06
     Productions
    0.06
    snapshot
    0.06
    Act Density 0.001%

    No Known Activations