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

    Neuronpedia

    INDEX
    Explanations

    free use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Princess
    0.38
    buscador
    0.37
     jaaye
    0.37
    Jeff
    0.36
     transducer
    0.36
    皇
    0.36
    aprendizaje
    0.36
     trab
    0.35
    Dado
    0.35
    ஶ
    0.35
    POSITIVE LOGITS
    不稳定
    0.45
    ated
    0.42
     Debit
    0.39
    anin
    0.38
    atted
    0.37
     emphasized
    0.37
    cal
    0.36
    ित
    0.36
    lected
    0.36
     Crews
    0.36
    Act Density 0.000%

    No Known Activations