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

    Neuronpedia

    INDEX
    Explanations

    border, text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unknown
    -0.07
     dear
    -0.07
    ERE
    -0.07
    :Object
    -0.06
     Managed
    -0.06
     trees
    -0.06
     profits
    -0.06
     elements
    -0.06
    맥
    -0.06
     Meter
    -0.06
    POSITIVE LOGITS
     rtl
    0.07
     fend
    0.06
     nebu
    0.06
     nackt
    0.06
     differentiation
    0.06
     lagi
    0.06
    _pdf
    0.06
     RTL
    0.06
    _BOTTOM
    0.06
     motivated
    0.06
    Act Density 0.004%

    No Known Activations