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

    Neuronpedia

    INDEX
    Explanations

    gifts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ping
    -0.06
    lds
    -0.06
     trajectory
    -0.06
    -"+
    -0.06
    	actual
    -0.06
     Showing
    -0.06
     مقدار
    -0.06
    itudes
    -0.06
     showing
    -0.06
    ytic
    -0.06
    POSITIVE LOGITS
    ра�
    0.07
    exual
    0.07
    ریف
    0.07
    _framework
    0.07
     WOM
    0.06
     향
    0.06
     gson
    0.06
    (note
    0.06
     prefixed
    0.06
    desc
    0.06
    Act Density 0.007%

    No Known Activations