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

    Neuronpedia

    INDEX
    Explanations

    expressions related to control and influence in social dynamics

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

    code identifiers and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.54
    ſelf
    -0.54
     $_"
    -0.53
     queſta
    -0.52
    migrationBuilder
    -0.51
     ujednoznacz
    -0.50
    ſelves
    -0.49
    |')
    -0.49
    httphttps
    -0.48
    ]=>
    -0.48
    POSITIVE LOGITS
    UserScript
    0.40
    withIdentifier
    0.38
    getKeyCode
    0.36
     достой
    0.35
    LEncoder
    0.35
    queryset
    0.34
    zewod
    0.34
    TargetException
    0.32
    衷
    0.32
     mis
    0.32
    Act Density 0.093%

    No Known Activations