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

    Neuronpedia

    INDEX
    Explanations

    igor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     امن
    -0.06
     comparing
    -0.06
     losses
    -0.06
     băng
    -0.06
     convenient
    -0.06
     carpet
    -0.06
    EM
    -0.06
     eu
    -0.06
     ayar
    -0.05
    realm
    -0.05
    POSITIVE LOGITS
    italize
    0.08
     नई
    0.07
    “(
    0.07
     flurry
    0.07
     mainAxisAlignment
    0.07
     deflate
    0.07
    juven
    0.07
    ặc
    0.07
    Insp
    0.07
    vanized
    0.07
    Act Density 0.016%

    No Known Activations