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

    Neuronpedia

    INDEX
    Explanations

    developer resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dashboard
    0.88
     consola
    0.87
    Note
    0.79
     Dashboard
    0.78
     datth
    0.78
    Dash
    0.78
    anah
    0.78
     dashes
    0.78
     Duma
    0.77
    kerk
    0.77
    POSITIVE LOGITS
    íng
    0.67
     मिर
    0.66
    stein
    0.64
    ストラップ
    0.63
    aguars
    0.63
    步
    0.63
     Verizon
    0.62
     Append
    0.62
     Parenting
    0.61
     symmetries
    0.61
    Act Density 0.001%

    No Known Activations