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

    Neuronpedia

    INDEX
    Explanations

    interpret/understand

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    রায়
    0.65
     Specification
    0.65
     імені
    0.64
    ઍ
    0.64
     buff
    0.63
     paisajes
    0.62
     उनके
    0.62
     Ferté
    0.62
     kanilang
    0.61
    瑗
    0.61
    POSITIVE LOGITS
    Arti
    0.65
    t
    0.63
    кса
    0.61
    Interpretation
    0.59
    tip
    0.59
    וני
    0.58
    analytical
    0.58
    Interpret
    0.57
    )$\\
    0.56
    Teste
    0.56
    Act Density 0.000%

    No Known Activations