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

    Neuronpedia

    INDEX
    Explanations

    verify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -background
    -0.07
     sand
    -0.07
    _column
    -0.07
    -L
    -0.07
    _l
    -0.07
    坐
    -0.06
    _n
    -0.06
     congen
    -0.06
     caste
    -0.06
     passage
    -0.06
    POSITIVE LOGITS
    Verify
    0.08
    Ver
    0.08
     verify
    0.08
    reo
    0.07
     Ver
    0.07
    .verify
    0.07
    Check
    0.07
     verification
    0.07
    _verify
    0.07
    abilir
    0.07
    Act Density 0.014%

    No Known Activations