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

    Neuronpedia

    INDEX
    Explanations

    engine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WriteBarrier
    -0.07
    -category
    -0.07
    _organization
    -0.07
     отсутств
    -0.06
    á
    -0.06
    Services
    -0.06
     Chlor
    -0.06
    olvable
    -0.06
    azz
    -0.06
    iscrimination
    -0.06
    POSITIVE LOGITS
    Pressed
    0.08
    .runners
    0.07
    ламент
    0.07
    onclick
    0.07
    ivering
    0.07
     див
    0.06
     claiming
    0.06
     tên
    0.06
    estureRecognizer
    0.06
     litt
    0.06
    Act Density 0.008%

    No Known Activations