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

    Neuronpedia

    INDEX
    Explanations

    this followed by app, page, or day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ion
    0.71
    ua
    0.71
    ik
    0.68
    house
    0.68
    won
    0.67
    ja
    0.66
    anas
    0.66
    have
    0.65
    onta
    0.64
    ore
    0.63
    POSITIVE LOGITS
     oliva
    0.68
    ୬
    0.61
     OPERATION
    0.59
    ﺋ
    0.59
     opérateur
    0.58
    샘
    0.58
    ก
    0.57
    으로서
    0.57
    ੭
    0.57
    يد
    0.56
    Act Density 0.002%

    No Known Activations