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

    Neuronpedia

    INDEX
    Explanations

    watching shows/movies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tacoma
    -0.07
     Gazette
    -0.07
    Rank
    -0.06
    *M
    -0.06
    Wave
    -0.06
     around
    -0.06
    )!
    -0.06
     Randall
    -0.06
     Mari
    -0.06
    ested
    -0.06
    POSITIVE LOGITS
    benhavn
    0.07
     exploits
    0.06
    unsqueeze
    0.06
    placeholder
    0.06
    větší
    0.06
    INUX
    0.06
     khiển
    0.06
     ию
    0.06
    thesized
    0.06
    /.↵↵
    0.06
    Act Density 0.025%

    No Known Activations