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

    Neuronpedia

    INDEX
    Explanations

    CBS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Schneider
    -0.07
     Assertion
    -0.07
     gradient
    -0.07
     interests
    -0.07
     moon
    -0.07
     ratio
    -0.06
     vacancy
    -0.06
    :no
    -0.06
    .getFloat
    -0.06
     Listener
    -0.06
    POSITIVE LOGITS
    -au
    0.07
    при
    0.06
    inous
    0.06
    ační
    0.06
    188
    0.06
     tob
    0.06
     болез
    0.06
     будинку
    0.06
     '">'
    0.06
    ulti
    0.06
    Act Density 0.002%

    No Known Activations