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

    Neuronpedia

    INDEX
    Explanations

    Common sentence structure words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Supplier
    -0.07
     se
    -0.06
    -es
    -0.06
     irritating
    -0.06
    -turned
    -0.06
     Kaf
    -0.06
    .te
    -0.06
    /pass
    -0.06
    	action
    -0.06
     Pain
    -0.06
    POSITIVE LOGITS
    ashing
    0.06
    □□
    0.06
    ода
    0.06
     웹사이트
    0.06
    Alarm
    0.06
     threading
    0.06
     alignment
    0.06
     Thank
    0.06
    istogram
    0.06
    ●●
    0.06
    Act Density 0.170%

    No Known Activations