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

    Neuronpedia

    INDEX
    Explanations

    organizations and companies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EXT
    -0.07
    iştir
    -0.07
    840
    -0.07
    -duration
    -0.06
    ीत
    -0.06
     frivol
    -0.06
    yw
    -0.06
     aides
    -0.06
    (cap
    -0.06
     Ма
    -0.06
    POSITIVE LOGITS
     складі
    0.08
     derail
    0.06
    腦
    0.06
     practically
    0.06
    teki
    0.06
    anean
    0.06
    posted
    0.06
    .sd
    0.06
    reon
    0.06
     enumerate
    0.05
    Act Density 0.026%

    No Known Activations