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

    Neuronpedia

    INDEX
    Explanations

    evidence of claims regarding legal charges and accusations

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

    Statements of falsehood or pretense

    np_acts-logits-general · gemini-2.0-flash

    falsehood and deception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CodedInputStream
    -0.63
     [*]
    -0.52
     onOptions
    -0.51
    endphp
    -0.50
    libatkan
    -0.48
     足
    -0.48
     amanecer
    -0.47
     impli
    -0.47
     canter
    -0.47
     gatto
    -0.46
    POSITIVE LOGITS
     fake
    0.93
     hoax
    0.85
     faked
    0.82
    fake
    0.81
     faking
    0.78
     bogus
    0.77
     false
    0.77
    FAKE
    0.72
     falsos
    0.72
     falsely
    0.70
    Act Density 0.443%

    No Known Activations