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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ustos
    -0.07
    álido
    -0.07
    bud
    -0.07
     bad
    -0.07
     lille
    -0.06
    illow
    -0.06
    ())->
    -0.06
     sad
    -0.06
     reporter
    -0.06
    mj
    -0.06
    POSITIVE LOGITS
    .getResponse
    0.07
     Pare
    0.07
    ρες
    0.07
     книж
    0.06
    >\<
    0.06
    .ev
    0.06
    	org
    0.06
     ί
    0.06
     coincidence
    0.06
    ümüzde
    0.06
    Act Density 0.014%

    No Known Activations