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

    Neuronpedia

    INDEX
    Explanations

    robust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iliated
    -0.07
    -place
    -0.07
    éra
    -0.07
    یل
    -0.07
     strcpy
    -0.07
     chí
    -0.07
    onal
    -0.06
     cil
    -0.06
     clic
    -0.06
     sınav
    -0.06
    POSITIVE LOGITS
     robust
    0.13
     toughness
    0.07
     Modules
    0.07
    ab
    0.07
     tab
    0.07
    ob
    0.07
     Dynamics
    0.06
     rigs
    0.06
     топ
    0.06
     Top
    0.06
    Act Density 0.005%

    No Known Activations