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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sayıda
    -0.07
    Pot
    -0.07
     PDT
    -0.06
    Bo
    -0.06
    .randint
    -0.06
     fabric
    -0.06
     Sind
    -0.06
    تا
    -0.06
    نش
    -0.06
     Vul
    -0.06
    POSITIVE LOGITS
     lights
    0.08
     которого
    0.06
     Lights
    0.06
    (xy
    0.06
     Sus
    0.06
     uncertain
    0.06
     inner
    0.06
    (sd
    0.06
     Ου
    0.06
     lesbi
    0.06
    Act Density 0.007%

    No Known Activations