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

    Neuronpedia

    INDEX
    Explanations

    driving, focused, object-oriented, self-driving, service-oriented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.64
    IC
    0.62
    م
    0.55
    ER
    0.55
    ות
    0.55
    एस
    0.54
    り
    0.53
    es
    0.52
    ান
    0.51
    ES
    0.51
    POSITIVE LOGITS
    0.61
    ^
    0.52
    ?
    0.49
    <
    0.47
    är
    0.46
     are
    0.45
    &
    0.44
    wich
    0.42
    -
    0.42
    ering
    0.41
    Act Density 0.788%

    No Known Activations