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

    Neuronpedia

    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    โจ
    -0.07
    319
    -0.07
     pier
    -0.07
    Bookmark
    -0.06
    ичес
    -0.06
    Disney
    -0.06
    َد
    -0.06
    unei
    -0.06
    _literals
    -0.06
    78
    -0.06
    POSITIVE LOGITS
    schedule
    0.07
    	font
    0.07
     charge
    0.06
    ",-
    0.06
    받
    0.06
    署
    0.06
    .Active
    0.06
     چنان
    0.06
     uphill
    0.06
     Char
    0.06
    Act Density 0.023%

    No Known Activations