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

    Neuronpedia

    INDEX
    Explanations

    copy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (main
    -0.07
    ्वत
    -0.06
     IGNORE
    -0.06
     mute
    -0.06
     jihad
    -0.06
    _PAGES
    -0.06
     Jian
    -0.06
    '*
    -0.06
    Throws
    -0.06
     ayında
    -0.06
    POSITIVE LOGITS
    escort
    0.08
     hippoc
    0.06
    .disc
    0.06
     서
    0.06
     copy
    0.06
     kil
    0.06
    _contacts
    0.06
     Chester
    0.06
    、そう
    0.06
    Scalars
    0.06
    Act Density 0.001%

    No Known Activations