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

    Neuronpedia

    INDEX
    Explanations

    nearly almost everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ann
    0.81
    ful
    0.78
    fully
    0.76
    ed
    0.72
    oyed
    0.71
    ighting
    0.70
     red
    0.68
    anned
    0.68
    akre
    0.68
     HRS
    0.68
    POSITIVE LOGITS
    Số
    0.90
    ۲
    0.89
    Resistance
    0.86
     ಉಪ
    0.83
     kesk
    0.83
    Energie
    0.82
     siguientes
    0.82
    particles
    0.82
     gagal
    0.82
     meios
    0.82
    Act Density 0.000%

    No Known Activations