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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avra
    -0.07
     cele
    -0.06
     antivirus
    -0.06
    oints
    -0.06
     Mobility
    -0.06
    XMLElement
    -0.06
    _gift
    -0.06
     CONSTANT
    -0.06
    Iter
    -0.06
     dementia
    -0.06
    POSITIVE LOGITS
     atheists
    0.07
    zb
    0.07
     trespass
    0.06
    .True
    0.06
    циклопед
    0.06
    bear
    0.06
    екту
    0.06
     upgrade
    0.06
    اس
    0.06
     druhý
    0.06
    Act Density 0.014%

    No Known Activations