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

    Neuronpedia

    INDEX
    Explanations

    between two

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ែក
    0.87
    公路
    0.87
     spécialement
    0.84
    <unused1082>
    0.79
     Egal
    0.79
    pere
    0.79
     genealogy
    0.79
    🌿
    0.78
     heredity
    0.77
     ইউরোপ
    0.77
    POSITIVE LOGITS
     NOTICE
    0.80
     Notice
    0.71
     c
    0.69
     inv
    0.66
    esc
    0.65
     um
    0.63
    Ca
    0.62
     रौ
    0.60
    NOTICE
    0.60
    C
    0.59
    Act Density 0.001%

    No Known Activations