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

    Neuronpedia

    INDEX
    Explanations

    frequency adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bundle
    -0.07
    Warn
    -0.06
     Dissertation
    -0.06
    dato
    -0.06
     Psychology
    -0.06
    axios
    -0.06
     leds
    -0.06
    	height
    -0.05
     Brewery
    -0.05
     felt
    -0.05
    POSITIVE LOGITS
     сильно
    0.07
    Wave
    0.07
     saving
    0.07
     NSK
    0.06
    -update
    0.06
     شی
    0.06
     naive
    0.06
    raig
    0.06
    ammable
    0.06
    ни
    0.06
    Act Density 0.071%

    No Known Activations