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

    Neuronpedia

    INDEX
    Explanations

    AAAA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    court
    -0.06
     pueblo
    -0.06
     από
    -0.06
     pev
    -0.06
     BR
    -0.06
     Judith
    -0.06
     Ocak
    -0.06
    _hours
    -0.06
     Roe
    -0.06
     Roch
    -0.06
    POSITIVE LOGITS
    addGap
    0.07
    .neg
    0.07
     Extras
    0.07
    -mount
    0.06
    mie
    0.06
    /manage
    0.06
    /mit
    0.06
     Од
    0.06
    ptions
    0.06
     touch
    0.06
    Act Density 0.004%

    No Known Activations