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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on forum‐style header notices about guest viewing restrictions and limited access to content.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     calibration
    -0.07
     exc
    -0.07
    isks
    -0.06
    леж
    -0.06
    -built
    -0.06
    reading
    -0.06
     recreation
    -0.06
     builder
    -0.06
    igated
    -0.06
     Calibration
    -0.06
    POSITIVE LOGITS
     SYMBOL
    0.06
    _secret
    0.06
     přítom
    0.06
     तरफ
    0.06
    eydi
    0.06
    (tol
    0.06
    %",↵
    0.06
     setBackgroundColor
    0.06
    εύ
    0.06
     těž
    0.06
    Act Density 0.001%

    No Known Activations