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

    Neuronpedia

    INDEX
    Explanations

    Scientific experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Owens
    -0.07
    (EX
    -0.07
     शक
    -0.07
    OUN
    -0.07
     yeast
    -0.07
     μ
    -0.06
     установлен
    -0.06
    .SECONDS
    -0.06
    _PCIE
    -0.06
    .ViewHolder
    -0.06
    POSITIVE LOGITS
     caution
    0.06
    ství
    0.06
    attern
    0.06
    stance
    0.06
    ……。
    0.06
    acist
    0.06
     Lionel
    0.06
    cko
    0.06
    _literals
    0.06
     stuff
    0.05
    Act Density 0.926%

    No Known Activations