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

    Neuronpedia

    INDEX
    Explanations

    correlations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BUTTONDOWN
    -0.07
     держ
    -0.06
     мене
    -0.06
    (Bundle
    -0.06
     userEmail
    -0.06
     Standards
    -0.06
     methyl
    -0.06
    }s
    -0.06
     =================================================================================
    -0.06
     Alman
    -0.06
    POSITIVE LOGITS
     mơ
    0.06
    swick
    0.06
    among
    0.06
    again
    0.06
    Brand
    0.06
    ्तम
    0.06
    eter
    0.06
     cubes
    0.06
    جی
    0.06
     freq
    0.06
    Act Density 0.140%

    No Known Activations