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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    פלסטיני
    -0.07
    ⏫
    -0.07
    🦋
    -0.07
    🤧
    -0.07
     isSelected
    -0.07
     صلى
    -0.07
    🤠
    -0.07
    可通过
    -0.07
    핀
    -0.06
    .photos
    -0.06
    POSITIVE LOGITS
     incumb
    0.08
    ⼭
    0.07
    שות
    0.07
     moments
    0.07
     enim
    0.07
    ète
    0.07
    _Array
    0.06
    _comm
    0.06
    emachine
    0.06
     wk
    0.06
    Act Density 0.009%

    No Known Activations