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

    Neuronpedia

    INDEX
    Explanations

    code configuration files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reachable
    0.43
     reachable
    0.43
     First
    0.40
     Flip
    0.40
     सहायक
    0.39
     Quadratic
    0.39
    âmica
    0.38
     каж
    0.38
     achievable
    0.38
     Meld
    0.37
    POSITIVE LOGITS
     darkMode
    0.50
     defineConfig
    0.46
     progetti
    0.43
     linii
    0.42
    ,//
    0.42
     antennes
    0.41
    plugins
    0.40
    历史上
    0.40
    ignores
    0.40
     magasiner
    0.39
    Act Density 0.002%

    No Known Activations