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

    Neuronpedia

    INDEX
    Explanations

    interact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neurons
    -0.07
    olu
    -0.06
    [int
    -0.06
    agenta
    -0.06
    iyor
    -0.06
     cents
    -0.06
    amma
    -0.06
    \widgets
    -0.06
    	send
    -0.06
     Fern
    -0.05
    POSITIVE LOGITS
    ити
    0.07
     měst
    0.07
    -ca
    0.06
    IONS
    0.06
     Мор
    0.06
     Currently
    0.06
    '}}>↵
    0.06
    	has
    0.06
     kterém
    0.06
     дія
    0.06
    Act Density 0.009%

    No Known Activations