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

    Neuronpedia

    INDEX
    Explanations

    translation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Grid
    -0.07
    _age
    -0.06
    .ends
    -0.06
    \Core
    -0.06
     obr
    -0.06
     Bang
    -0.06
     caution
    -0.06
    ('.')
    -0.06
    _eta
    -0.06
    _Ent
    -0.06
    POSITIVE LOGITS
    Carbon
    0.06
     COMMON
    0.06
    areth
    0.06
    不同
    0.06
     Decom
    0.06
    альный
    0.06
    ();↵↵↵
    0.06
    *******************************************************************************/↵
    0.06
    advance
    0.06
    _mirror
    0.06
    Act Density 0.046%

    No Known Activations