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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     landscapes
    -0.07
    hatt
    -0.06
     CAS
    -0.06
    _boundary
    -0.06
     breed
    -0.06
     landscape
    -0.06
     lovers
    -0.06
     otherwise
    -0.06
     forms
    -0.06
    Associate
    -0.06
    POSITIVE LOGITS
     자
    0.07
     missing
    0.07
    вищ
    0.07
    ไม
    0.06
    <>("
    0.06
     جام
    0.06
     هست
    0.06
    ’y
    0.06
    　ヾ
    0.06
     départ
    0.06
    Act Density 0.018%

    No Known Activations