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

    Neuronpedia

    INDEX
    Explanations

    truth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     *
    -0.07
    *N
    -0.06
    bro
    -0.06
     Json
    -0.06
    _INIT
    -0.06
     nickname
    -0.06
     ←
    -0.06
    ocese
    -0.06
     clinic
    -0.06
    _increment
    -0.06
    POSITIVE LOGITS
     truth
    0.15
    truth
    0.08
    资金
    0.06
     truthful
    0.06
    _REGEX
    0.06
    ght
    0.06
    CanBe
    0.06
     rahat
    0.06
    _truth
    0.06
    equip
    0.06
    Act Density 0.004%

    No Known Activations