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

    Neuronpedia

    INDEX
    Explanations

    ambient or room temperature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astră
    -1.14
     kuu
    -1.08
     lâng
    -1.05
     lavage
    -1.02
    泐
    -1.01
    ACIONAL
    -1.00
    Formazione
    -0.98
     față
    -0.96
     ſuch
    -0.95
     puntu
    -0.95
    POSITIVE LOGITS
     днем
    1.27
    veien
    1.06
     although
    1.05
    ☀️
    1.04
    Semitism
    1.01
    这项
    1.00
     or
    0.99
    $),
    0.96
     greeting
    0.96
    ),"
    0.95
    Act Density 0.020%

    No Known Activations