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

    Neuronpedia

    INDEX
    Explanations

    relays, towers, hollow-body, arium

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وعلى
    2.06
    联动
    1.59
     almonds
    1.55
    resTmp
    1.52
     RBIs
    1.46
     casings
    1.44
     NPs
    1.36
    ೋಜನ
    1.34
     collaborateurs
    1.34
    𒆜
    1.34
    POSITIVE LOGITS
    .
    1.94
    t
    1.92
    За
    1.86
    5
    1.73
    >
    1.71
    7
    1.71
    И
    1.70
    u
    1.70
    하여
    1.69
    Ба
    1.67
    Act Density 0.001%

    No Known Activations