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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (U
    -0.07
    �
    -0.07
    delta
    -0.07
     Am
    -0.06
    想到
    -0.06
     youre
    -0.06
    =$('#
    -0.06
    (Mod
    -0.06
    iddle
    -0.06
     рук
    -0.06
    POSITIVE LOGITS
    .SimpleDateFormat
    0.07
     bureaucrats
    0.06
     vitro
    0.06
    ा↵↵
    0.06
     wheel
    0.06
    Struct
    0.06
     TN
    0.06
    .semantic
    0.06
     transporting
    0.06
    ()↵↵
    0.06
    Act Density 0.020%

    No Known Activations