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

    Neuronpedia

    INDEX
    Explanations

    Scientific formulas and models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DD
    -0.08
    deme
    -0.07
    Dev
    -0.07
    accom
    -0.07
    XA
    -0.06
     dementia
    -0.06
     Waves
    -0.06
    ем
    -0.06
     ruin
    -0.06
     guilty
    -0.06
    POSITIVE LOGITS
     večer
    0.06
    _instances
    0.06
     الاح
    0.06
    seller
    0.06
    ]=]
    0.06
    <AudioSource
    0.06
    _loop
    0.06
    /Instruction
    0.06
    sterdam
    0.06
     |_
    0.06
    Act Density 0.023%

    No Known Activations