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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Group
    -0.07
    ()↵↵↵↵
    -0.07
    .aggregate
    -0.07
    {↵↵
    -0.07
     velocity
    -0.07
    ()
    -0.07
    }↵↵↵↵
    -0.06
    ^
    -0.06
    还记得
    -0.06
    (action
    -0.06
    POSITIVE LOGITS
    עשה
    0.08
    STRUCT
    0.08
    DEFINED
    0.07
    马桶
    0.07
     ListTile
    0.07
    arna
    0.07
     PCS
    0.07
     świe
    0.06
     stove
    0.06
    _),
    0.06
    Act Density 0.000%

    No Known Activations