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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nevertheless
    -0.07
    -0.07
    ’t
    -0.07
    Mor
    -0.06
     any
    -0.06
    seeing
    -0.06
     che
    -0.06
    't
    -0.06
    	StringBuilder
    -0.06
    -rated
    -0.06
    POSITIVE LOGITS
     Shoes
    0.08
    iculos
    0.07
     SWT
    0.07
    (IOException
    0.07
     parchment
    0.07
    瓶
    0.07
    */
↵
↵
    0.07
     FileAccess
    0.06
    _BAND
    0.06
     hashtable
    0.06
    Act Density 0.020%

    No Known Activations