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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Luckily
    -0.07
     мист
    -0.06
    -fill
    -0.06
     hog
    -0.06
    apper
    -0.06
     majority
    -0.06
     Fram
    -0.06
    aldo
    -0.06
    _isr
    -0.06
     aluno
    -0.06
    POSITIVE LOGITS
    .construct
    0.07
    _constants
    0.07
     operators
    0.06
    _AVAILABLE
    0.06
    .coroutines
    0.06
    _custom
    0.06
     розташ
    0.06
     Springfield
    0.06
    =target
    0.06
     Saf
    0.06
    Act Density 0.095%

    No Known Activations