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

    Neuronpedia

    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erialize
    -0.07
     '?'
    -0.06
     не
    -0.06
    ımızın
    -0.06
     petitions
    -0.06
    .comment
    -0.06
     Mits
    -0.06
    .load
    -0.06
    _written
    -0.06
    _skip
    -0.06
    POSITIVE LOGITS
     dụ
    0.07
     tog
    0.07
    .gb
    0.07
    .ForeignKey
    0.06
    uild
    0.06
    andbox
    0.06
     exec
    0.06
    -half
    0.06
    OO
    0.06
    374
    0.06
    Act Density 0.010%

    No Known Activations