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

    Neuronpedia

    INDEX
    Explanations

    CSS styling classes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2157>
    0.80
    <unused319>
    0.79
     एमएन
    0.79
     lng
    0.78
    <unused569>
    0.78
    <unused1001>
    0.77
     Fm
    0.77
     Π
    0.77
    Ｆ
    0.76
    Pda
    0.76
    POSITIVE LOGITS
     "
    0.81
     "$
    0.74
     “
    0.73
    &#
    0.71
     "`
    0.69
    `
    0.68
    0.67
    '`
    0.66
    '
    0.66
    രു
    0.64
    Act Density 0.001%

    No Known Activations