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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     요
    -0.07
     pistols
    -0.07
    .sort
    -0.07
     Folder
    -0.06
     بسبب
    -0.06
    暴
    -0.06
     проведення
    -0.06
    	lines
    -0.06
    difficulty
    -0.06
     cafe
    -0.06
    POSITIVE LOGITS
     erot
    0.06
    umar
    0.06
    _COM
    0.06
     陳
    0.06
    ati
    0.06
    ancing
    0.06
     viral
    0.06
     _
↵
    0.06
     universal
    0.06
    avenous
    0.06
    Act Density 0.004%

    No Known Activations