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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     newsp
    -0.07
     betrayed
    -0.06
    ريط
    -0.06
    ẵ
    -0.06
    ertest
    -0.06
    alyze
    -0.06
    ใหญ
    -0.06
    burse
    -0.06
     changing
    -0.06
    erce
    -0.06
    POSITIVE LOGITS
    \V
    0.07
    _HAL
    0.06
    _Block
    0.06
    _FB
    0.06
     trance
    0.06
    (">
    0.06
     건
    0.06
     Stamford
    0.06
     chore
    0.06
    цький
    0.06
    Act Density 0.008%

    No Known Activations