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

    Neuronpedia

    INDEX
    Explanations

    dates and time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    circ
    -0.08
     fort
    -0.07
    ACS
    -0.07
     Yale
    -0.07
    _save
    -0.07
     Glo
    -0.06
    	Created
    -0.06
    Throws
    -0.06
     Fort
    -0.06
    .Permission
    -0.06
    POSITIVE LOGITS
    LOB
    0.07
    ！”
    0.07
     ﾊ
    0.06
                    
    0.06
    ",-
    0.06
     strands
    0.06
    мент
    0.06
     bla
    0.06
    /http
    0.06
     saldır
    0.06
    Act Density 0.004%

    No Known Activations