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

    Neuronpedia

    INDEX
    Explanations

    book titles and authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urname
    0.47
     Begriffe
    0.46
    bsch
    0.44
     Brahmin
    0.43
    nostic
    0.43
    瞋
    0.43
     Beziehung
    0.43
    äus
    0.42
     personenbez
    0.42
    𓂀
    0.42
    POSITIVE LOGITS
    C
    0.48
    )|
    0.47
     T
    0.38
     multi
    0.37
     ,
    0.37
     C
    0.37
    D
    0.36
     Res
    0.36
    T
    0.36
    +
    0.36
    Act Density 0.000%

    No Known Activations