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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subdued
    -0.08
     Gain
    -0.07
     NaN
    -0.07
    ADIO
    -0.07
     haf
    -0.07
    pais
    -0.07
    illions
    -0.07
     conductor
    -0.06
    tings
    -0.06
     woo
    -0.06
    POSITIVE LOGITS
    	ptr
    0.07
     şirket
    0.07
     Nichols
    0.06
     courage
    0.06
     persuade
    0.06
    ‬↵
    0.06
    _br
    0.06
    مم
    0.06
    Agregar
    0.06
    250
    0.06
    Act Density 0.007%

    No Known Activations