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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PCS
    -0.07
     LF
    -0.06
    IFIED
    -0.06
     Proto
    -0.06
    DeltaTime
    -0.06
     RCMP
    -0.06
    基地
    -0.06
    raith
    -0.06
    _fsm
    -0.06
     ultimately
    -0.06
    POSITIVE LOGITS
    ़त
    0.06
    occupation
    0.06
    disable
    0.06
    Warning
    0.06
     minha
    0.06
    addresses
    0.06
    oli
    0.06
    How
    0.06
    >>();↵↵
    0.06
    :T
    0.06
    Act Density 0.006%

    No Known Activations