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

    Neuronpedia

    INDEX
    Explanations

    city

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mates
    -0.07
     글
    -0.07
    ôte
    -0.06
    OMBRE
    -0.06
     hashing
    -0.06
     evid
    -0.06
     tha
    -0.06
     zombies
    -0.06
    _OBJ
    -0.06
    こう
    -0.06
    POSITIVE LOGITS
    __((
    0.07
     čist
    0.07
    _since
    0.07
     //-
    0.07
     pł
    0.07
     ensure
    0.06
     Ensure
    0.06
     delic
    0.06
    lose
    0.06
     faker
    0.06
    Act Density 0.009%

    No Known Activations