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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     successor
    -0.07
     Mü
    -0.07
     diarrhea
    -0.06
    ellen
    -0.06
    "),↵
    -0.06
     yoluyla
    -0.06
     υπάρχ
    -0.06
    -designed
    -0.06
    exampleInput
    -0.06
     treated
    -0.06
    POSITIVE LOGITS
    -dat
    0.06
     Shin
    0.06
     ejec
    0.06
     Exec
    0.06
    ieving
    0.06
     bezpečnost
    0.06
    іст
    0.06
     wherein
    0.06
    ése
    0.06
    ByUsername
    0.06
    Act Density 0.003%

    No Known Activations