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

    Neuronpedia

    INDEX
    Explanations

    Expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucht
    -0.08
    铩
    -0.08
    km
    -0.07
     Starts
    -0.07
    SM
    -0.07
    _DETECT
    -0.07
    isos
    -0.07
    �
    -0.06
    ieten
    -0.06
    纻
    -0.06
    POSITIVE LOGITS
    adjust
    0.07
    垢
    0.07
     Graves
    0.07
    nell
    0.07
     clay
    0.07
    .Reporting
    0.07
     aquarium
    0.07
    แก
    0.07
    灰尘
    0.07
     interle
    0.07
    Act Density 0.009%

    No Known Activations