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

    Neuronpedia

    INDEX
    Explanations

    Technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     happening
    -0.06
    fight
    -0.06
     sight
    -0.06
     sollten
    -0.06
     willingly
    -0.06
     ramps
    -0.06
     돌
    -0.06
     daddy
    -0.06
    だよ
    -0.06
     conspic
    -0.06
    POSITIVE LOGITS
    食品
    0.07
    news
    0.07
    صول
    0.06
    _mode
    0.06
    lak
    0.06
     retention
    0.06
    InputLabel
    0.06
    �
    0.06
     Conditional
    0.06
     امور
    0.06
    Act Density 0.001%

    No Known Activations