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

    Neuronpedia

    INDEX
    Explanations

    development and related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     `=`,
    1.27
    σης
    1.25
    𝘬
    1.20
    류
    1.19
     `<`,
    1.18
     andet
    1.18
     `>`,
    1.17
     называют
    1.17
    値
    1.16
    wander
    1.12
    POSITIVE LOGITS
    ן
    1.85
    alanine
    1.52
    खंड
    1.50
    ន៍
    1.44
    轫
    1.40
    մ
    1.38
     nez
    1.37
     isotherm
    1.36
    م
    1.36
     çevre
    1.36
    Act Density 0.070%

    No Known Activations