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

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INED
    -0.07
     difficile
    -0.06
    enticated
    -0.06
    ý
    -0.06
    .stamp
    -0.06
    ienne
    -0.06
     Depos
    -0.06
    =>$
    -0.06
    grave
    -0.06
     supporters
    -0.06
    POSITIVE LOGITS
     Stability
    0.08
    ness
    0.08
     familiarity
    0.07
    (skill
    0.07
     brilliance
    0.07
    teness
    0.07
    ability
    0.07
     پا
    0.07
     consistency
    0.07
    Whether
    0.07
    Act Density 0.372%

    No Known Activations