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

    Neuronpedia

    INDEX
    Explanations

    re-election and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    espoir
    0.57
    𝗮
    0.57
     Economies
    0.55
     História
    0.55
     아직
    0.54
     archived
    0.53
     Sudan
    0.53
     Ashanti
    0.53
     Restaurants
    0.52
    ॉन
    0.52
    POSITIVE LOGITS
    علم
    0.55
    th
    0.53
    0.51
    pw
    0.49
     consecut
    0.48
    ng
    0.48
    0.47
    attributes
    0.47
    سبب
    0.46
    JComboBox
    0.46
    Act Density 0.007%

    No Known Activations