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

    Neuronpedia

    INDEX
    Explanations

    question words and help resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.80
    _
    0.65
     afield
    0.63
    onents
    0.61
    /<
    0.61
    omaly
    0.58
    beiter
    0.57
    𝓙
    0.57
    /=
    0.57
    /@
    0.57
    POSITIVE LOGITS
    what
    0.89
    wp
    0.88
     cómo
    0.82
    how
    0.81
    signs
    0.80
    如何
    0.79
    What
    0.79
    Cómo
    0.78
     cuánto
    0.78
     如何
    0.76
    Act Density 0.040%

    No Known Activations