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

    Neuronpedia

    INDEX
    Explanations

    references to supernatural events and their consequences

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

    ending in "er"

    np_acts-logits-general · gemini-2.0-flash

    thunder, Scatter, cluster, finger, parameter, timer activations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    skosten
    -0.71
    surfaces
    -0.67
    salon
    -0.67
    glEnable
    -0.65
    ymo
    -0.64
    tenths
    -0.64
    IActionResult
    -0.64
    hdashline
    -0.63
     CommonModule
    -0.63
    topus
    -0.63
    POSITIVE LOGITS
    er
    1.19
    ized
    1.05
    ization
    1.05
    ised
    0.87
    rrrrrrrr
    0.86
    ed
    0.84
    theless
    0.81
    rrrr
    0.81
    ize
    0.76
    ous
    0.76
    Act Density 0.632%

    No Known Activations