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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    constant
    -0.07
    Limits
    -0.06
    .bottomAnchor
    -0.06
    PB
    -0.06
    ynomial
    -0.06
     pylab
    -0.06
    uk
    -0.06
    uto
    -0.06
     rau
    -0.06
    folios
    -0.06
    POSITIVE LOGITS
     hist
    0.06
     αστ
    0.06
    主义
    0.06
     emanc
    0.06
    Phys
    0.06
     Mỹ
    0.06
    _By
    0.06
    —at
    0.06
    _opt
    0.06
     Ghost
    0.06
    Act Density 0.008%

    No Known Activations