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

    Neuronpedia

    INDEX
    Explanations

    contextually significant phrases related to observations, experiences, and nuanced expressions of thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    always is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zwiſchen
    -0.76
    ſelben
    -0.72
    ſammen
    -0.71
    ︐
    -0.71
     unſer
    -0.71
     ſelbſt
    -0.71
     tartalo
    -0.70
     erſten
    -0.69
    <pad>
    -0.69
    [@BOS@]
    -0.69
    POSITIVE LOGITS
     normally
    0.31
    pyx
    0.28
    mi
    0.28
    setWindow
    0.28
     gambe
    0.28
    MD
    0.27
    ↵↵
    0.26
     ProtoMessage
    0.26
    !
    0.26
    ni
    0.26
    Act Density 0.110%

    No Known Activations