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

    Neuronpedia

    INDEX
    Explanations

    flags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Jul
    -0.07
     Россий
    -0.07
    projection
    -0.06
    Decoration
    -0.06
    Clr
    -0.06
    .Basic
    -0.06
     director
    -0.06
     legality
    -0.06
     і
    -0.06
    偷
    -0.06
    POSITIVE LOGITS
    rokes
    0.07
    ologia
    0.07
    ourg
    0.07
     devour
    0.07
     asiat
    0.07
    альную
    0.06
    avia
    0.06
     تجربه
    0.06
     अपन
    0.06
    ANNEL
    0.06
    Act Density 0.012%

    No Known Activations