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

    Neuronpedia

    INDEX
    Explanations

    famoso por

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incroy
    0.47
     Mulder
    0.47
     उच्चारण
    0.45
    зацию
    0.43
    ехал
    0.43
     cinéma
    0.43
     flound
    0.43
    瘋
    0.42
     natthi
    0.42
    icletas
    0.40
    POSITIVE LOGITS
    with
    0.40
    Od
    0.38
     stiff
    0.37
     od
    0.37
    Seg
    0.36
    Int
    0.36
    ILER
    0.36
    基
    0.36
    Comprehensive
    0.35
    溅
    0.35
    Act Density 0.001%

    No Known Activations