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

    Neuronpedia

    INDEX
    Explanations

    ""

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ียงใหม
    -0.07
    ْ
    -0.07
    وش
    -0.06
    -responsive
    -0.06
     thải
    -0.06
    ENDING
    -0.06
    training
    -0.06
     filmpjes
    -0.06
    'av
    -0.06
     pleas
    -0.06
    POSITIVE LOGITS
    /m
    0.07
    Cl
    0.07
    Searching
    0.07
    golden
    0.07
     Kosovo
    0.06
    _ele
    0.06
     Biography
    0.06
     Himal
    0.06
     Started
    0.06
     ℝ
    0.06
    Act Density 0.001%

    No Known Activations