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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    슬
    -0.07
    literal
    -0.06
    :[
    -0.06
     conducting
    -0.06
     realization
    -0.06
    _overflow
    -0.06
     Literal
    -0.06
     treating
    -0.06
    ela
    -0.06
    dash
    -0.06
    POSITIVE LOGITS
     밤
    0.07
    vae
    0.07
     destinationViewController
    0.06
    	sort
    0.06
     Derm
    0.06
     EVE
    0.06
     troops
    0.06
     vốn
    0.06
    '][$
    0.06
    ICTURE
    0.06
    Act Density 0.002%

    No Known Activations