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

    Neuronpedia

    INDEX
    Explanations

    defense

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Counter
    -0.08
     distribution
    -0.07
    477
    -0.06
    .hist
    -0.06
     vhod
    -0.06
     birkaç
    -0.06
    brands
    -0.06
     bột
    -0.06
     Plants
    -0.06
     distributions
    -0.06
    POSITIVE LOGITS
     anarch
    0.07
    ese
    0.06
     acept
    0.06
    uitar
    0.06
     catast
    0.06
     considering
    0.06
    _SELF
    0.06
     род
    0.06
     робота
    0.06
     dissip
    0.06
    Act Density 0.062%

    No Known Activations