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

    Neuronpedia

    INDEX
    Explanations

    DTD

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Trim
    -0.07
    .capitalize
    -0.07
    _pair
    -0.06
     Twitch
    -0.06
    ancock
    -0.06
    елефон
    -0.06
    312
    -0.06
    Place
    -0.06
     Seal
    -0.06
     Nou
    -0.06
    POSITIVE LOGITS
    ')));↵↵
    0.07
     biod
    0.07
     città
    0.07
    delegate
    0.06
     loosen
    0.06
    tid
    0.06
    DTD
    0.06
    ceae
    0.06
    buyer
    0.06
    ãeste
    0.06
    Act Density 0.000%

    No Known Activations