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

    Neuronpedia

    INDEX
    Explanations

    third

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mustered
    0.90
    W
    0.87
    M
    0.83
    θυ
    0.83
    are
    0.82
     Purpose
    0.82
     eyeing
    0.82
     elongated
    0.82
     ascertained
    0.81
     erupted
    0.81
    POSITIVE LOGITS
     причем
    1.03
    他
    1.00
    𝘰
    0.93
    𝘦
    0.92
    ઓને
    0.90
    {
    0.90
    𝘶
    0.89
    𝘴
    0.88
    లు
    0.86
     plufieurs
    0.85
    Act Density 0.093%

    No Known Activations