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

    Neuronpedia

    INDEX
    Explanations

    half

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tic
    -0.08
    erties
    -0.08
    .y
    -0.08
     issues
    -0.08
    ;)
    -0.08
     phú
    -0.07
    ?"
    -0.07
    ;"
    -0.07
    Md
    -0.07
     pose
    -0.07
    POSITIVE LOGITS
     kami
    0.08
    ⵀ
    0.07
    ありが
    0.07
     verbess
    0.07
    ᄂ
    0.07
     archived
    0.06
    ünün
    0.06
    .enterprise
    0.06
     OF
    0.06
    슌
    0.06
    Act Density 0.002%

    No Known Activations