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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ).
↵
    -0.07
     numb
    -0.06
     PTS
    -0.06
    Chess
    -0.06
    strncmp
    -0.06
    Lets
    -0.06
     referral
    -0.06
     Vert
    -0.06
     '$
    -0.06
     |>
    -0.06
    POSITIVE LOGITS
    _rec
    0.07
     işç
    0.07
    _tt
    0.06
    (DIS
    0.06
    ्तम
    0.06
    _DD
    0.06
    Units
    0.06
    ΠΑ
    0.06
     Constructs
    0.06
    (proc
    0.06
    Act Density 0.010%

    No Known Activations