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

    Neuronpedia

    INDEX
    Explanations

    conditional logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     substantially
    -0.07
     begin
    -0.07
     meille
    -0.06
     zou
    -0.06
     Mid
    -0.06
     frogs
    -0.06
     Q
    -0.06
     gang
    -0.06
    _FORE
    -0.06
     remar
    -0.06
    POSITIVE LOGITS
     عشق
    0.06
    (sprintf
    0.06
    Evaluator
    0.06
    屏
    0.06
    :*
    0.06
     ایست
    0.06
    DOCKER
    0.06
    uling
    0.06
     неск
    0.06
    'post
    0.06
    Act Density 0.004%

    No Known Activations