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

    Neuronpedia

    INDEX
    Explanations

    fig

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agues
    -0.07
     Backend
    -0.07
     да
    -0.07
     mammals
    -0.06
     leur
    -0.06
     Hundred
    -0.06
     cured
    -0.06
    enefit
    -0.06
     Salvation
    -0.06
     bigger
    -0.06
    POSITIVE LOGITS
    olk
    0.06
    DK
    0.06
    (glm
    0.06
    ‌تر
    0.06
    ,[],
    0.06
    abric
    0.06
    UpdatedAt
    0.06
    (cli
    0.06
     Bul
    0.06
     vazgeç
    0.06
    Act Density 0.001%

    No Known Activations