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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     рівень
    -0.07
    Work
    -0.06
     ры
    -0.06
     collapse
    -0.06
     млн
    -0.06
     Critical
    -0.06
     tým
    -0.06
    활동
    -0.06
     Skills
    -0.06
     Někter
    -0.06
    POSITIVE LOGITS
    gmail
    0.07
    Club
    0.07
    .repositories
    0.07
    TECTED
    0.07
    ampler
    0.07
    IPLE
    0.06
    itez
    0.06
    amples
    0.06
    ede
    0.06
    clair
    0.06
    Act Density 0.077%

    No Known Activations