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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vet
    -0.06
    をお
    -0.06
     CreateUser
    -0.06
     Melissa
    -0.06
     Tân
    -0.06
    ."\
    -0.06
     malloc
    -0.06
    Blob
    -0.06
     nale
    -0.06
    	W
    -0.06
    POSITIVE LOGITS
    abolic
    0.07
    CTR
    0.07
    /archive
    0.07
     vacancies
    0.06
     zad
    0.06
    tility
    0.06
     rady
    0.06
     ByteBuffer
    0.06
    점
    0.06
    rega
    0.06
    Act Density 0.048%

    No Known Activations