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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ابه
    -0.07
     eo
    -0.07
     disrespectful
    -0.06
     ух
    -0.06
    랫
    -0.06
     답
    -0.06
     arrogant
    -0.06
     ژان
    -0.06
    Sparse
    -0.06
    sparse
    -0.06
    POSITIVE LOGITS
     invitation
    0.07
    Strike
    0.07
    rogate
    0.06
    ilmington
    0.06
    .',↵
    0.06
     excludes
    0.06
    takes
    0.06
    provided
    0.06
    imately
    0.06
    ROLL
    0.06
    Act Density 0.000%

    No Known Activations