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

    Neuronpedia

    INDEX
    Explanations

    By followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     llevo
    0.88
    ளமான
    0.74
     Webber
    0.74
     fortes
    0.73
     possível
    0.73
    വിത
    0.73
     noh
    0.71
    iophorus
    0.71
     inscrito
    0.71
    zás
    0.70
    POSITIVE LOGITS
     stealing
    0.90
     way
    0.78
    George
    0.75
     George
    0.73
    GEORGE
    0.72
     theft
    0.71
     advancing
    0.71
     GEORGE
    0.70
    By
    0.70
     By
    0.69
    Act Density 0.000%

    No Known Activations