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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety or warnings

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

    Currency, numerical values, or codes

    np_acts-logits-general · gemini-2.0-flash

    money amounts and currency symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الدراسه
    -0.64
    msgTypes
    -0.59
    amerikanischer
    -0.57
     <<<<<<<<<<<<<<
    -0.57
     Folsom
    -0.56
    mistic
    -0.56
     мәкал
    -0.55
     sapi
    -0.54
    caya
    -0.53
     Spill
    -0.53
    POSITIVE LOGITS
    EDEFAULT
    0.63
    OrWhiteSpace
    0.57
    CastException
    0.53
    httphttps
    0.51
    )";
    0.50
    Collected
    0.49
    collected
    0.49
    ]';
    0.49
    tahui
    0.49
     R
    0.48
    Act Density 0.040%

    No Known Activations