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

    Neuronpedia

    INDEX
    Explanations

    Parentheses/operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Weak
    -0.07
    Com
    -0.07
     fragile
    -0.06
    °C
    -0.06
    III
    -0.06
    atonin
    -0.06
    _cs
    -0.06
    rous
    -0.06
    ality
    -0.06
    "',↵
    -0.06
    POSITIVE LOGITS
     gdk
    0.07
    .fake
    0.07
    께
    0.07
    ahkan
    0.07
     intriguing
    0.07
    ORTH
    0.07
    <UnityEngine
    0.06
     blev
    0.06
     Boise
    0.06
     ill
    0.06
    Act Density 0.011%

    No Known Activations