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

    Neuronpedia

    INDEX
    Explanations

    -k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SAM
    -0.06
     кам
    -0.06
    magnitude
    -0.06
    NCY
    -0.06
     Satan
    -0.06
     facets
    -0.06
     tide
    -0.06
    nection
    -0.06
     Honour
    -0.06
    umo
    -0.06
    POSITIVE LOGITS
     tomato
    0.07
    .alt
    0.07
     )↵↵↵
    0.06
    Classes
    0.06
    985
    0.06
     Yog
    0.06
    ạt
    0.06
    ург
    0.06
     vintage
    0.06
    CP
    0.06
    Act Density 0.000%

    No Known Activations