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

    Neuronpedia

    INDEX
    Explanations

    young

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istik
    -0.27
     racked
    -0.25
    禧
    -0.25
    iaux
    -0.25
    çĽĬ
    -0.24
    ITCH
    -0.24
    illo
    -0.24
    庵
    -0.23
    ibr
    -0.23
    ä¹ĭä½ľ
    -0.23
    POSITIVE LOGITS
    é¢ĦåijĬ
    0.28
    符åı·
    0.28
    kees
    0.28
    MPI
    0.27
    æľĪä¸Ń
    0.27
    preced
    0.26
     !");↵
    0.25
    绦
    0.25
    ctions
    0.24
    processors
    0.24
    Act Density 0.001%

    No Known Activations