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

    Neuronpedia

    INDEX
    Explanations

    timeout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hmm
    -0.08
    -0.07
    اره
    -0.07
    ści
    -0.07
    -0.07
     Cheese
    -0.07
     creepy
    -0.07
     OZ
    -0.07
     **/↵↵
    -0.07
    وعية
    -0.07
    POSITIVE LOGITS
    activate
    0.09
     activate
    0.08
     strategic
    0.08
    activar
    0.08
     activa
    0.08
     hid
    0.07
    activ
    0.07
     presencial
    0.07
     Latvia
    0.07
     ceb
    0.07
    Act Density 0.002%
    No Known Activations