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

    Neuronpedia

    INDEX
    Explanations

    factual writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     pensar
    -0.06
    爷
    -0.06
    $obj
    -0.06
     corpse
    -0.06
     яр
    -0.06
     frozen
    -0.06
    Ÿ
    -0.06
     بالم
    -0.06
    чества
    -0.06
    POSITIVE LOGITS
     runnable
    0.07
    _COND
    0.07
     *
    0.06
     `}↵
    0.06
     Diff
    0.06
    .DEBUG
    0.06
    urally
    0.06
    Assembler
    0.06
     Saga
    0.06
    _LITERAL
    0.06
    Act Density 0.070%

    No Known Activations