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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Showing
    -0.06
     northwest
    -0.06
    _plus
    -0.06
    preci
    -0.06
     Representation
    -0.06
    _pull
    -0.06
     worldwide
    -0.06
    Div
    -0.06
     lifted
    -0.06
     defamation
    -0.06
    POSITIVE LOGITS
     Kendrick
    0.07
     اصول
    0.07
    abbix
    0.06
     بیمار
    0.06
    ●●
    0.06
    CppMethod
    0.06
     >",
    0.06
    bách
    0.06
     creatively
    0.06
    ınıf
    0.06
    Act Density 0.005%

    No Known Activations