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

    Neuronpedia

    INDEX
    Explanations

    Feelings about time

    np_max-act · gemini-2.0-flash

    The neuron detects emotionally charged or introspective words—terms expressing feelings, intensity, or uncertainty (e.g. pain, never, like).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Loads
    -0.07
     باشند
    -0.07
     :)
    -0.06
     sanit
    -0.06
     consultancy
    -0.06
     podpor
    -0.06
    si
    -0.06
     cite
    -0.06
     insurance
    -0.06
     지난
    -0.06
    POSITIVE LOGITS
    .DisplayName
    0.07
    fix
    0.06
    .drawable
    0.06
    .createdAt
    0.06
    ?,?,?,?,
    0.06
    },{↵
    0.06
    .os
    0.06
    áb
    0.06
    cantidad
    0.06
     ┃
    0.06
    Act Density 0.037%

    No Known Activations