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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     ignorance
    -0.07
     مه
    -0.07
    킨
    -0.07
     المه
    -0.07
    ango
    -0.07
    엔
    -0.07
     Depot
    -0.06
     misleading
    -0.06
     Hizmet
    -0.06
    POSITIVE LOGITS
     following
    0.09
    following
    0.07
    Following
    0.07
     Following
    0.07
    !")
↵
    0.06
    [--
    0.06
    .smtp
    0.06
     personalize
    0.06
    례
    0.06
    !.↵↵
    0.06
    Act Density 0.030%

    No Known Activations