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

    Neuronpedia

    INDEX
    Explanations

    Disjointed text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Box
    -0.06
     outro
    -0.06
     FUNC
    -0.06
     tsl
    -0.06
    できます
    -0.06
    158
    -0.06
     IQ
    -0.06
    	action
    -0.06
     spreading
    -0.06
    유
    -0.05
    POSITIVE LOGITS
    ической
    0.08
    VENT
    0.07
     startActivityForResult
    0.07
     standout
    0.07
    UBLIC
    0.07
    .startswith
    0.07
    STONE
    0.06
    ，都
    0.06
     تلك
    0.06
    _most
    0.06
    Act Density 0.000%

    No Known Activations