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

    Neuronpedia

    INDEX
    Explanations

    Chemical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lers
    -0.06
     Vulcan
    -0.06
    -0.06
     clocks
    -0.06
     relocation
    -0.06
     Temperature
    -0.06
    Toe
    -0.06
    	default
    -0.06
    더니
    -0.06
    ッカー
    -0.06
    POSITIVE LOGITS
     describing
    0.06
     citas
    0.06
     verificar
    0.06
    ovna
    0.06
     fif
    0.06
     соглас
    0.06
     dangling
    0.06
     shines
    0.06
    Special
    0.06
    писание
    0.05
    Act Density 0.014%

    No Known Activations