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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ooky
    -0.06
     Cricket
    -0.06
    abad
    -0.06
    -Feb
    -0.06
    otos
    -0.06
     '/
    -0.06
    dar
    -0.06
    auled
    -0.06
    うち
    -0.06
    956
    -0.06
    POSITIVE LOGITS
     tou
    0.07
    ね
    0.06
    .dequeueReusableCell
    0.06
     denial
    0.06
     motor
    0.06
     omnip
    0.06
    izione
    0.06
     prominence
    0.06
    .blue
    0.06
     backbone
    0.06
    Act Density 0.001%

    No Known Activations