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

    Neuronpedia

    INDEX
    Explanations

    .g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horny
    -0.07
    stood
    -0.07
     appar
    -0.07
     commercials
    -0.06
     дея
    -0.06
     тепер
    -0.06
     NSString
    -0.06
     ATK
    -0.06
     measurable
    -0.06
    348
    -0.06
    POSITIVE LOGITS
    ểm
    0.07
    ق
    0.07
     insp
    0.07
    .sales
    0.06
     guest
    0.06
     بد
    0.06
    śmy
    0.06
    ład
    0.06
    .J
    0.06
    Acknowled
    0.06
    Act Density 0.025%

    No Known Activations