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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    你要
    -0.07
    抵押
    -0.07
    ὰ
    -0.07
     Amendment
    -0.06
    �
    -0.06
    📠
    -0.06
    @PostMapping
    -0.06
     Male
    -0.06
     AssemblyTitle
    -0.06
    jąc
    -0.06
    POSITIVE LOGITS
    compet
    0.07
    креп
    0.07
    Weapons
    0.07
    楽し
    0.07
     martial
    0.07
     Related
    0.07
     dum
    0.07
    DATED
    0.07
    _div
    0.07
     impover
    0.07
    Act Density 0.077%

    No Known Activations