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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FIT
    -0.07
    .ly
    -0.06
    EA
    -0.06
    En
    -0.06
    Histogram
    -0.06
    _NONE
    -0.06
     libre
    -0.06
     تس
    -0.06
    ;";↵
    -0.06
     almond
    -0.06
    POSITIVE LOGITS
     nedenle
    0.07
     overwhelmingly
    0.06
    _comb
    0.06
     honeymoon
    0.06
    Population
    0.06
     However
    0.06
     równ
    0.06
    	Data
    0.06
     Viking
    0.06
     Inform
    0.06
    Act Density 0.009%

    No Known Activations