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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.10
     सं
    -0.09
    -0.09
     ئۆ
    -0.08
    قدمة
    -0.08
     bewegen
    -0.08
     gaining
    -0.08
     читать
    -0.07
     Polis
    -0.07
     Prestige
    -0.07
    POSITIVE LOGITS
    -mail
    0.08
    lip
    0.08
     maupun
    0.08
    ilic
    0.08
    ert
    0.08
     registrados
    0.08
    &C
    0.08
    \Mail
    0.07
    lish
    0.07
    yellow
    0.07
    Act Density 0.023%
    No Known Activations