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

    Neuronpedia

    INDEX
    Explanations

    maritime and overland

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ູ່
    0.57
     splendour
    0.56
     vuelos
    0.55
     housewives
    0.54
    Therates
    0.52
     regalías
    0.52
     ausschließlich
    0.52
     regering
    0.51
     اقصیٰ
    0.51
    FBSDKError
    0.51
    POSITIVE LOGITS
    ↵
    0.75
    -
    0.67
     (
    0.64
    /
    0.64
    ↵↵
    0.60
    .
    0.58
    B
    0.58
    (
    0.58
    ,
    0.57
    \
    0.57
    Act Density 0.004%

    No Known Activations