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

    Neuronpedia

    INDEX
    Explanations

    hot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Email
    -0.06
    στό
    -0.06
    .defaults
    -0.06
    (car
    -0.06
     squarely
    -0.06
     такие
    -0.06
     Jaguar
    -0.06
    amax
    -0.06
    	ds
    -0.06
    Funny
    -0.06
    POSITIVE LOGITS
    (Sprite
    0.07
     Yardım
    0.06
    ии
    0.06
    wią
    0.06
    artic
    0.06
     ú
    0.06
    conte
    0.06
     hombre
    0.06
     pozit
    0.06
    .utility
    0.06
    Act Density 0.010%

    No Known Activations