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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gr
    -0.07
    urved
    -0.07
     Challenge
    -0.06
    LV
    -0.06
     vorhand
    -0.06
     виріш
    -0.06
    стві
    -0.06
    "N
    -0.06
    nění
    -0.06
    _primitive
    -0.06
    POSITIVE LOGITS
    ify
    0.07
     nữa
    0.07
    padding
    0.06
     showcased
    0.06
     perf
    0.06
    emos
    0.06
     вдруг
    0.06
    qualified
    0.06
    coin
    0.05
     periodically
    0.05
    Act Density 0.000%

    No Known Activations