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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by years or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.77
    ,
    0.71
     Attempt
    0.71
    ?
    0.71
    )
    0.69
     Falling
    0.68
     F
    0.67
     Surgeons
    0.67
    '
    0.65
    t
    0.64
    POSITIVE LOGITS
    getto
    0.80
    modations
    0.72
    酸化
    0.71
    
    0.71
    ética
    0.69
    基础设施
    0.68
     ocurrido
    0.66
    渡し
    0.66
     badań
    0.66
    庻
    0.66
    Act Density 0.000%

    No Known Activations