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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jee
    -0.07
     венти
    -0.07
     게시물
    -0.07
     Hungarian
    -0.07
     možná
    -0.06
     imposs
    -0.06
     хорошо
    -0.06
     //////////////////////////////////////////////////////////////////////////
    -0.06
    Indexed
    -0.06
     náz
    -0.06
    POSITIVE LOGITS
     bankers
    0.06
     муж
    0.06
     lith
    0.06
    coln
    0.06
    oris
    0.06
    ^^
    0.06
    '.
    0.06
    Directories
    0.06
    .LocalDateTime
    0.06
    sty
    0.06
    Act Density 0.001%

    No Known Activations