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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paper
    -0.07
    =""
    -0.07
     woes
    -0.06
    afa
    -0.06
    emed
    -0.06
    eye
    -0.06
     involuntary
    -0.06
    _week
    -0.06
    *t
    -0.06
    olu
    -0.06
    POSITIVE LOGITS
    fish
    0.10
    .Expect
    0.08
    \Validation
    0.07
     стан
    0.07
    Fish
    0.07
    ıntı
    0.07
    iyesi
    0.07
    _false
    0.07
     DIM
    0.07
    jpg
    0.06
    Act Density 0.000%

    No Known Activations