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

    Neuronpedia

    INDEX
    Explanations

    differentiating normal from abnormal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .za
    -0.08
    _$
    -0.07
     зрост
    -0.07
     ql
    -0.07
     taskId
    -0.07
     Posting
    -0.06
     quadr
    -0.06
     деся
    -0.06
    ıldı
    -0.06
     OpCode
    -0.06
    POSITIVE LOGITS
    Å
    0.06
    relay
    0.06
    running
    0.06
    Interactive
    0.06
     turnout
    0.06
    	types
    0.06
    bool
    0.06
    こと
    0.06
    -drive
    0.06
    anson
    0.06
    Act Density 0.002%

    No Known Activations