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

    Neuronpedia

    INDEX
    Explanations

    Code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Soph
    -0.07
     Tout
    -0.07
     Дж
    -0.07
    uron
    -0.06
     Opp
    -0.06
     Soph
    -0.06
     Jud
    -0.06
    .Java
    -0.06
     Ign
    -0.06
    -0.06
    POSITIVE LOGITS
    commission
    0.07
     :↵
    0.06
    mess
    0.06
    ional
    0.06
    нями
    0.06
    ⌒
    0.06
    letters
    0.06
    will
    0.06
    .decor
    0.06
    oloji
    0.06
    Act Density 0.000%

    No Known Activations