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

    Neuronpedia

    INDEX
    Explanations

    code/data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Direction
    -0.06
    (di
    -0.06
     Graphics
    -0.06
    _alloc
    -0.06
     صح
    -0.06
     Duplicate
    -0.06
    itched
    -0.05
     SCN
    -0.05
    antic
    -0.05
     sandwich
    -0.05
    POSITIVE LOGITS
     Thái
    0.07
     того
    0.07
     Hö
    0.06
    _credentials
    0.06
    prov
    0.06
     slab
    0.06
     Вс
    0.06
     repayment
    0.06
     خودرو
    0.06
     přátel
    0.06
    Act Density 0.033%

    No Known Activations