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

    Neuronpedia

    INDEX
    Explanations

    Poseidon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.71
    ру
    0.68
    ری
    0.68
    з
    0.64
    so
    0.64
    ле
    0.64
    но
    0.61
    っ
    0.61
    ler
    0.59
    rt
    0.56
    POSITIVE LOGITS
    ’
    0.61
    ാവ
    0.58
    ’;
    0.57
    ั้น
    0.56
    H
    0.55
     gubernatorial
    0.54
     congressional
    0.53
     congressman
    0.53
     motorsport
    0.53
     outcry
    0.53
    Act Density 0.000%

    No Known Activations