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

    Neuronpedia

    INDEX
    Explanations

    ag

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liar
    -0.06
     climbed
    -0.06
    .multiply
    -0.06
     validations
    -0.06
     fourth
    -0.06
    Mgr
    -0.06
     cyclists
    -0.06
    .glide
    -0.06
    ライン
    -0.06
    _pay
    -0.06
    POSITIVE LOGITS
     гал
    0.07
     practical
    0.06
     SYSTEM
    0.06
     생각
    0.06
     εργ
    0.06
     crossword
    0.06
     recipro
    0.06
     запах
    0.06
     beyond
    0.06
    根
    0.06
    Act Density 0.001%

    No Known Activations