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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Equals
    -0.07
    לו
    -0.07
    essoa
    -0.07
    infos
    -0.07
    OURS
    -0.07
    lemn
    -0.07
    _EXIST
    -0.07
    规格
    -0.07
    teen
    -0.07
    .Update
    -0.07
    POSITIVE LOGITS
    (B
    0.07
     当
    0.07
     founding
    0.07
     />
↵
    0.06
    ”↵
    0.06
     PROGMEM
    0.06
     Kirk
    0.06
     Dedicated
    0.06
    Which
    0.06
    ()</
    0.06
    Act Density 0.035%

    No Known Activations