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

    Neuronpedia

    INDEX
    Explanations

    electromagnetic interference

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CHA
    -0.07
     SUS
    -0.07
    领取
    -0.07
    preter
    -0.07
    חמ
    -0.07
     cuer
    -0.07
     Obt
    -0.06
    🎒
    -0.06
    _CHO
    -0.06
    ፈ
    -0.06
    POSITIVE LOGITS
    .Linked
    0.07
     restricting
    0.07
    .Requires
    0.07
     alterations
    0.07
    (Parameter
    0.07
     contaminants
    0.07
    predict
    0.07
     Pixels
    0.07
     strip
    0.07
     marginRight
    0.07
    Act Density 0.029%

    No Known Activations