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

    Neuronpedia

    INDEX
    Explanations

    sequences of colons and their associated values

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

    time of day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.42
     թվական
    -0.38
    tonsoft
    -0.35
    propTypes
    -0.34
     plegable
    -0.33
     vendus
    -0.32
    ientí
    -0.30
     året
    -0.30
     guapos
    -0.30
     صوتيه
    -0.30
    POSITIVE LOGITS
     kasarigan
    0.74
    DockStyle
    0.65
    principalColumn
    0.62
     afternoon
    0.62
    RegressionTest
    0.61
     Afternoon
    0.59
    afternoon
    0.58
     evening
    0.57
     Evening
    0.56
     HOUR
    0.56
    Act Density 0.009%

    No Known Activations