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

    Neuronpedia

    INDEX
    Explanations

    language codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    橦
    0.93
     resto
    0.88
     sleepy
    0.84
    在于
    0.80
    ская
    0.79
     capítulo
    0.79
     gripped
    0.79
     temática
    0.78
     profissional
    0.77
     profundo
    0.77
    POSITIVE LOGITS
    I
    1.03
    IL
    1.02
    Ook
    1.02
    Aging
    1.01
    X
    1.01
    Aqu
    1.00
    C
    0.99
    AL
    0.98
    Aq
    0.98
    Io
    0.97
    Act Density 0.000%

    No Known Activations