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

    Neuronpedia

    INDEX
    Explanations

    ì¤ followed by ĺ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ëĦ¤ìĿ´íĬ¸
    -0.12
    ãĥ»ãĥ»ãĥ»\n\n
    -0.10
    oops
    -0.10
    .nz
    -0.09
    adge
    -0.09
    _ISR
    -0.09
     ë¸
    -0.09
    timezone
    -0.09
    .Apis
    -0.09
    iosper
    -0.09
    POSITIVE LOGITS
    Į
    0.11
    igo
    0.10
    į
    0.10
     cred
    0.09
    ĺ
    0.09
    asp
    0.09
    orget
    0.09
    ong
    0.09
     perfect
    0.09
     Thanks
    0.09
    Act Density 0.012%

    No Known Activations