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

    Neuronpedia

    INDEX
    Explanations

    say hashtag

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (columns
    -0.07
     Worth
    -0.07
     assigning
    -0.06
     Населення
    -0.06
     Last
    -0.06
    disabled
    -0.06
     CONTRIBUT
    -0.06
    (Name
    -0.06
    (dest
    -0.06
    _every
    -0.06
    POSITIVE LOGITS
    uale
    0.06
    νου
    0.06
    Sa
    0.06
     Cli
    0.06
     zase
    0.06
     Palestin
    0.06
    ]["
    0.05
     самостоятель
    0.05
    (System
    0.05
    ンス
    0.05
    Act Density 0.044%

    No Known Activations