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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _impl
    -0.08
     Sunni
    -0.07
    	sql
    -0.07
     DLL
    -0.06
    %%*/
    -0.06
    Stride
    -0.06
     luxurious
    -0.06
     base
    -0.06
     jednou
    -0.06
     goed
    -0.06
    POSITIVE LOGITS
    eguard
    0.07
    _NR
    0.07
     Daten
    0.06
    背
    0.06
    ंक
    0.06
     network
    0.06
    orge
    0.06
    ие
    0.06
     can
    0.06
    esting
    0.06
    Act Density 0.023%

    No Known Activations