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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Haar
    -0.08
     Fairfax
    -0.08
    847
    -0.08
     Herr
    -0.07
     polyval
    -0.07
     Hai
    -0.07
     loops
    -0.07
     herd
    -0.07
     Zert
    -0.07
    ยน
    -0.07
    POSITIVE LOGITS
     선언
    0.12
     ঘোষ
    0.11
     formulation
    0.10
    Declaration
    0.10
     declaration
    0.10
     declarations
    0.10
     ಘ
    0.09
     articulation
    0.09
    Crusher
    0.09
     declarar
    0.09
    Act Density 0.042%

    No Known Activations