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

    Neuronpedia

    INDEX
    Explanations

    Roboto

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ¿
    -0.07
     Heading
    -0.07
     bomb
    -0.07
    ccd
    -0.07
     economist
    -0.07
    elt
    -0.07
    andan
    -0.07
    ök
    -0.07
    נסיבות
    -0.06
     Exploration
    -0.06
    POSITIVE LOGITS
    ⬡
    0.07
     правило
    0.07
    ;m
    0.07
    .import
    0.07
    (Blueprint
    0.07
    _numero
    0.07
    几家
    0.07
     regul
    0.07
    roulette
    0.07
    -random
    0.07
    Act Density 0.003%

    No Known Activations