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

    Neuronpedia

    INDEX
    Explanations

    German language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interact
    -0.07
    proc
    -0.07
     badly
    -0.06
     dö
    -0.06
     signer
    -0.06
    arna
    -0.06
     pornografia
    -0.06
     =
↵
    -0.06
     Clo
    -0.06
     paradox
    -0.06
    POSITIVE LOGITS
    ToBounds
    0.07
    _SK
    0.07
     elapsed
    0.07
     лич
    0.06
    vell
    0.06
     Blacks
    0.06
    	EIF
    0.06
     Sebastian
    0.06
    仅
    0.06
    -helper
    0.06
    Act Density 0.060%

    No Known Activations