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

    Neuronpedia

    INDEX
    Explanations

    break

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    强
    -0.07
     contents
    -0.07
    Person
    -0.07
    Supplier
    -0.06
     الدول
    -0.06
     above
    -0.06
     Patterson
    -0.06
     Esther
    -0.06
    誉
    -0.06
    stem
    -0.06
    POSITIVE LOGITS
    _er
    0.07
     휴
    0.07
     breaks
    0.06
    (hdc
    0.06
    _tls
    0.06
    CKET
    0.06
     помогает
    0.06
     inset
    0.06
     mají
    0.06
    하시
    0.06
    Act Density 0.011%

    No Known Activations