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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unquestion
    -0.07
     kes
    -0.07
    uales
    -0.07
     üç
    -0.06
     SMS
    -0.06
     nichž
    -0.06
    	url
    -0.06
     اث
    -0.06
     FileManager
    -0.06
     dispersed
    -0.06
    POSITIVE LOGITS
     hd
    0.08
    丽
    0.07
     spd
    0.06
     actions
    0.06
    false
    0.06
    size
    0.06
     tweaks
    0.06
    同時
    0.06
    τσι
    0.06
    hid
    0.06
    Act Density 0.047%

    No Known Activations