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

    Neuronpedia

    INDEX
    Explanations

    Filed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ryan
    -0.06
    ,title
    -0.06
    umbs
    -0.06
    ليات
    -0.06
    需求
    -0.06
     Bart
    -0.06
     Welch
    -0.06
     hw
    -0.06
    abant
    -0.06
     dB
    -0.06
    POSITIVE LOGITS
    _List
    0.07
     venir
    0.07
     }
↵
↵
    0.07
     không
    0.07
    ा।↵↵
    0.06
     elle
    0.06
     mixins
    0.06
    inand
    0.06
    FW
    0.06
    idis
    0.06
    Act Density 0.000%

    No Known Activations