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

    Neuronpedia

    INDEX
    Explanations

    joint parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ObjectMapper
    0.47
     ዝ
    0.39
    üss
    0.37
     ተጨማሪ
    0.37
    дри
    0.36
     setSnackbar
    0.36
    FBSDKError
    0.36
    Bitmap
    0.35
    ấm
    0.35
    resolved
    0.35
    POSITIVE LOGITS
     tarifas
    0.42
    铖
    0.38
    👖
    0.38
     Educator
    0.37
    Iteration
    0.35
     harnesses
    0.35
     tariffs
    0.35
     educate
    0.34
     educator
    0.34
     tradeoffs
    0.34
    Act Density 0.000%

    No Known Activations