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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.75
    __(/*!
    -0.74
    ly
    -0.69
    HomeAsUpEnabled
    -0.68
     numberWith
    -0.65
    principalTable
    -0.62
    ropoda
    -0.60
    loit
    -0.59
    itarianism
    -0.59
    UrlResolution
    -0.59
    POSITIVE LOGITS
    Release
    0.46
     Paz
    0.45
     dispatch
    0.43
    <bos>
    0.43
    opress
    0.42
     dispatched
    0.42
    Paz
    0.41
     paz
    0.41
    redux
    0.41
     peacefully
    0.41
    Act Density 0.014%

    No Known Activations