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

    Neuronpedia

    INDEX
    Explanations

    settling down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hist
    -0.07
    close
    -0.07
    requete
    -0.07
    -su
    -0.07
     desc
    -0.07
    '},
    -0.06
    Null
    -0.06
     clums
    -0.06
     antagonist
    -0.06
    --}}↵
    -0.06
    POSITIVE LOGITS
     내려
    0.07
    amera
    0.06
     Jag
    0.06
    ΑΝ
    0.06
     قدر
    0.06
    ARTH
    0.06
     золот
    0.06
    orman
    0.06
    /The
    0.06
     склад
    0.06
    Act Density 0.029%

    No Known Activations