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

    Neuronpedia

    INDEX
    Explanations

    software versions and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     স্টোন
    0.39
    uates
    0.38
     Danny
    0.37
    Danny
    0.36
     styled
    0.36
     JERSEY
    0.35
    ুনের
    0.35
     aquí
    0.35
    anía
    0.34
     matières
    0.34
    POSITIVE LOGITS
     summer
    0.54
    Summer
    0.47
    summer
    0.47
    夏
    0.46
     Summer
    0.45
    Winter
    0.45
     winter
    0.45
    冬
    0.44
    HF
    0.44
    Q
    0.44
    Act Density 0.004%

    No Known Activations