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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    †
    -0.08
     Lam
    -0.08
    oss
    -0.07
    冒
    -0.07
     кишеч
    -0.07
    IMATION
    -0.07
     lashes
    -0.07
    chmal
    -0.07
     �
    -0.07
     bö
    -0.07
    POSITIVE LOGITS
     maka
    0.09
    0.08
     loci
    0.08
    -rate
    0.08
     rozd
    0.08
    .guna
    0.08
    _G
    0.08
     locus
    0.08
     点
    0.08
    któ
    0.07
    Act Density 0.013%
    No Known Activations