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
    藩
    -0.07
    მ
    -0.07
    lie
    -0.07
    iPhone
    -0.07
     Falling
    -0.07
    ragment
    -0.07
    琉
    -0.07
     İnt
    -0.06
    Candidate
    -0.06
     Diamond
    -0.06
    POSITIVE LOGITS
    .xyz
    0.08
    .score
    0.08
    廒
    0.07
    око
    0.07
     produces
    0.07
    .vn
    0.06
    蝓
    0.06
    (slug
    0.06
    ,end
    0.06
    ˓
    0.06
    Act Density 0.117%

    No Known Activations