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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ads
    -0.07
    _related
    -0.06
    estar
    -0.06
    Road
    -0.06
     Worce
    -0.06
    gressor
    -0.06
     defenses
    -0.06
     допомаг
    -0.06
    estre
    -0.06
    交易
    -0.06
    POSITIVE LOGITS
    ♠
    0.06
    }//
    0.06
     関
    0.06
     interracial
    0.06
     shocked
    0.06
     interpol
    0.06
    Porn
    0.06
    .omg
    0.06
     Chow
    0.06
    ρκεια
    0.06
    Act Density 0.016%

    No Known Activations