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

    Neuronpedia

    INDEX
    Explanations

    What questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Evil
    -0.07
    Escape
    -0.07
    verty
    -0.07
     Escape
    -0.06
    IGO
    -0.06
    sphere
    -0.06
    phere
    -0.06
     Poverty
    -0.06
     poster
    -0.06
     éxito
    -0.06
    POSITIVE LOGITS
    .runners
    0.06
     проблем
    0.06
    ätz
    0.06
     onBlur
    0.06
    /target
    0.06
    .removeAttribute
    0.06
    .Local
    0.06
    	parser
    0.06
     innoc
    0.06
    TouchUpInside
    0.06
    Act Density 0.099%

    No Known Activations