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

    Neuronpedia

    INDEX
    Explanations

    does not exist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     매우
    -0.07
     апр
    -0.07
    ereço
    -0.07
    و
    -0.07
    ods
    -0.06
    	dialog
    -0.06
    کو
    -0.06
     congr
    -0.06
     blended
    -0.06
    /cpu
    -0.06
    POSITIVE LOGITS
    زارش
    0.06
    etically
    0.06
     Friend
    0.06
    _TRIGGER
    0.06
    İL
    0.06
    .ForeColor
    0.06
     Lal
    0.06
    Container
    0.06
     ):↵↵
    0.06
     проф
    0.05
    Act Density 0.062%

    No Known Activations