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

    Neuronpedia

    INDEX
    Explanations

    references to identities within code or configurations

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

    identity file, server, matrix, operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.59
     <>",
    -0.54
     للمعارف
    -0.51
    rrggbb
    -0.51
    Tikang
    -0.48
    RRect
    -0.48
     Infórmanos
    -0.48
    <![
    -0.48
     noDo
    -0.47
    runners
    -0.46
    POSITIVE LOGITS
     identity
    1.88
    identity
    1.77
     Identity
    1.74
    Identity
    1.63
     IDENTITY
    1.63
     identidad
    1.42
    IDENTITY
    1.39
     Identities
    1.33
     identité
    1.33
     identities
    1.32
    Act Density 0.007%

    No Known Activations