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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     it
    -0.08
     bowel
    -0.07
     social
    -0.07
    seudo
    -0.07
     expl
    -0.07
     Shield
    -0.06
     It
    -0.06
     goes
    -0.06
     these
    -0.06
     ين
    -0.06
    POSITIVE LOGITS
     громад
    0.07
    HEMA
    0.07
     Ξ
    0.06
     высокой
    0.06
     postId
    0.06
    _aligned
    0.06
    _cat
    0.06
    érc
    0.06
    ===============
    0.06
    environments
    0.06
    Act Density 0.101%

    No Known Activations