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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     For
    -0.09
    _to
    -0.08
     for
    -0.08
    For
    -0.08
    	FOR
    -0.07
     FOR
    -0.06
    144
    -0.06
    #for
    -0.06
    To
    -0.06
     طبي
    -0.06
    POSITIVE LOGITS
    ings
    0.07
     Ent
    0.07
     Moh
    0.07
    す
    0.07
    (Audio
    0.06
    ING
    0.06
     Cheers
    0.06
    lingen
    0.06
    INGS
    0.06
    lassen
    0.06
    Act Density 0.157%

    No Known Activations