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

    Neuronpedia

    INDEX
    Explanations

    __dirname and __filename

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     integrable
    0.43
    lič
    0.40
     Likely
    0.38
     afe
    0.38
     большое
    0.37
    ение
    0.37
    lecht
    0.36
    acr
    0.36
    ň
    0.36
     paling
    0.36
    POSITIVE LOGITS
    dirname
    0.46
    Investigators
    0.42
    Articles
    0.40
    Vancouver
    0.40
    House
    0.39
    Rew
    0.39
    णु
    0.39
     definit
    0.39
     направ
    0.38
    Def
    0.38
    Act Density 0.000%

    No Known Activations