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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TempVal
    0.87
    TempBuffer
    0.70
    ⌦
    0.69
    សំណ
    0.67
    ($('#
    0.64
    .$(
    0.64
    𝔪
    0.63
     deformations
    0.63
    Aqu
    0.62
    0.62
    POSITIVE LOGITS
    e
    0.92
    ité
    0.83
    ette
    0.83
    т
    0.82
    ksi
    0.82
    ième
    0.81
    ße
    0.80
    tere
    0.80
    ፊት
    0.79
    ς
    0.79
    Act Density 0.000%

    No Known Activations