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

    Neuronpedia

    INDEX
    Explanations

    anisotropy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seçim
    -0.07
     `${
    -0.06
     ｜
    -0.06
     fak
    -0.06
    ，因为
    -0.06
     PRICE
    -0.06
    Navig
    -0.06
     appetite
    -0.06
    .reflect
    -0.05
     geo
    -0.05
    POSITIVE LOGITS
    arity
    0.07
    ####
    0.07
    ression
    0.07
     Participation
    0.07
    ###
    0.07
    imité
    0.07
    ess
    0.07
     меньше
    0.06
    0.06
    یمی
    0.06
    Act Density 0.021%

    No Known Activations