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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ski
    -0.55
    yay
    -0.50
    gwt
    -0.49
    leri
    -0.48
    ly
    -0.47
     plane
    -0.46
    の
    -0.45
    u
    -0.45
     them
    -0.44
    ík
    -0.44
    POSITIVE LOGITS
     Efq
    0.81
     ſeveral
    0.78
     houſe
    0.76
    DoubleQuotes
    0.74
     resourceCulture
    0.73
     intptr
    0.73
     poffe
    0.72
     ſtate
    0.69
    Personendaten
    0.68
     feveral
    0.66
    Act Density 0.002%

    No Known Activations