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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RANK
    -0.07
    PathParam
    -0.06
     επα
    -0.06
     Crime
    -0.06
    acobian
    -0.06
     clin
    -0.06
    _REUSE
    -0.06
    _Tree
    -0.06
     surrounds
    -0.06
    may
    -0.06
    POSITIVE LOGITS
     szer
    0.06
    income
    0.06
     gunfire
    0.06
    aseña
    0.06
     ket
    0.06
    основ
    0.06
    щая
    0.06
     ters
    0.06
    lif
    0.06
     \$
    0.06
    Act Density 0.041%

    No Known Activations