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

    Neuronpedia

    INDEX
    Explanations

    later

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kvinnor
    -0.06
     Floral
    -0.06
    骑
    -0.06
    ’ya
    -0.06
     dialogs
    -0.06
     zaměstn
    -0.06
     USAGE
    -0.06
    cj
    -0.06
    _monitor
    -0.06
     ydk
    -0.06
    POSITIVE LOGITS
     kas
    0.07
    Insensitive
    0.07
     sharpen
    0.06
    Sch
    0.06
     svém
    0.06
     basketball
    0.06
     odst
    0.06
     Plymouth
    0.06
    ━━
    0.06
    ITT
    0.06
    Act Density 0.203%

    No Known Activations