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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     converter
    -0.07
     seeker
    -0.07
    άννης
    -0.06
     Vote
    -0.06
    ンク
    -0.06
     Armed
    -0.06
     Encrypt
    -0.06
    Marketing
    -0.06
     specifics
    -0.06
    _ADMIN
    -0.06
    POSITIVE LOGITS
    .UltraWin
    0.06
    ORIGINAL
    0.06
     tetas
    0.06
    .;.;.;.;
    0.06
    .parseLong
    0.06
     nome
    0.06
     Outer
    0.06
    PELL
    0.06
    _fil
    0.06
    .TimeUnit
    0.06
    Act Density 0.009%

    No Known Activations