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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shard
    -0.07
    vier
    -0.07
    lli
    -0.06
     UC
    -0.06
    Jac
    -0.06
     �
    -0.06
     �
    -0.06
     boarding
    -0.06
     POR
    -0.06
     winds
    -0.06
    POSITIVE LOGITS
    _hook
    0.06
    (itemView
    0.06
    .constants
    0.06
    .requires
    0.06
    ().'/
    0.06
    فاع
    0.06
    'être
    0.06
    چی
    0.06
    _success
    0.06
    .cls
    0.06
    Act Density 0.005%

    No Known Activations