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

    Neuronpedia

    INDEX
    Explanations

    Code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hor
    -0.07
    attended
    -0.06
    '},↵
    -0.06
     romantic
    -0.06
     clim
    -0.06
    _cp
    -0.06
     wizards
    -0.06
    cov
    -0.06
    _xt
    -0.06
     hub
    -0.06
    POSITIVE LOGITS
    /REC
    0.07
     OC
    0.07
     fakt
    0.06
    _CNT
    0.06
     Apostle
    0.06
    _thickness
    0.06
    >{$
    0.06
    ﻟ
    0.06
     بودن
    0.06
    опри
    0.06
    Act Density 0.144%

    No Known Activations