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

    Neuronpedia

    INDEX
    Explanations

    keyboard input events

    np_max-act · gemini-2.0-flash

    The neuron never produces any non‐zero activations and thus appears to be “dead” (it does not detect any pattern).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Coll
    -0.07
     retained
    -0.07
     RTAL
    -0.06
    정
    -0.06
    เด
    -0.06
    telefono
    -0.06
     �
    -0.06
    Gen
    -0.06
    Wis
    -0.06
     Thomas
    -0.06
    POSITIVE LOGITS
     searchTerm
    0.06
    oad
    0.06
    ounge
    0.06
    하려
    0.06
     thuốc
    0.06
    %，
    0.06
     Submit
    0.06
     Dietary
    0.06
    љ
    0.06
     размещ
    0.06
    Act Density 0.003%

    No Known Activations