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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Temp
    -0.07
     shitty
    -0.06
    .ham
    -0.06
     tiền
    -0.06
     ts
    -0.06
    i�
    -0.06
     устрой
    -0.06
     viable
    -0.06
     olma
    -0.06
    čemž
    -0.06
    POSITIVE LOGITS
    ++){
    0.07
    656
    0.07
     Gerard
    0.07
     HA
    0.07
     grup
    0.06
     Convention
    0.06
    ’m
    0.06
     г
    0.06
    emony
    0.06
    "group
    0.06
    Act Density 0.000%

    No Known Activations