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

    Neuronpedia

    INDEX
    Explanations

    iteration or calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Goodreads
    0.40
    సా
    0.37
    ॅप
    0.37
    崱
    0.37
    浱
    0.36
    ່ານ
    0.36
    ISource
    0.36
    梫
    0.36
    删
    0.36
    હેરા
    0.36
    POSITIVE LOGITS
    getLength
    0.38
     Nh
    0.37
     Wald
    0.37
     alamat
    0.37
    iciencia
    0.36
    icon
    0.36
     Verne
    0.36
     lunghezza
    0.36
     mal
    0.35
     durata
    0.35
    Act Density 0.002%

    No Known Activations