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

    Neuronpedia

    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xF
    -0.07
    rawler
    -0.07
    .ClientSize
    -0.06
    Sharp
    -0.06
    -chain
    -0.06
    ropy
    -0.06
    .mk
    -0.06
     bf
    -0.06
    oshi
    -0.06
    -binary
    -0.06
    POSITIVE LOGITS
    一种
    0.07
     vegetation
    0.07
     controvers
    0.06
     перест
    0.06
     separated
    0.06
    突
    0.06
    출
    0.06
     gunfire
    0.06
    挙
    0.06
     pos
    0.06
    Act Density 0.001%

    No Known Activations