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

    Neuronpedia

    INDEX
    Explanations

    clothing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ONENT
    -0.08
     debates
    -0.07
    ARED
    -0.07
     Sanders
    -0.06
    _stats
    -0.06
     Gray
    -0.06
     Statue
    -0.06
     Rams
    -0.06
    され
    -0.06
     emploi
    -0.06
    POSITIVE LOGITS
     mouseX
    0.07
     Fare
    0.07
    �
    0.06
     ㅇ
    0.06
     []*
    0.06
    ->___
    0.06
     Validators
    0.06
     WAN
    0.06
    WER
    0.06
     dejting
    0.06
    Act Density 0.046%

    No Known Activations