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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    占
    -0.06
    Ub
    -0.06
    _to
    -0.06
     shuffled
    -0.06
     secure
    -0.06
    resa
    -0.06
     Omega
    -0.05
     bk
    -0.05
    833
    -0.05
     dus
    -0.05
    POSITIVE LOGITS
     نمای
    0.07
    _SEARCH
    0.07
    ↵
    0.06
    .↵
    0.06
    스가
    0.06
    ственный
    0.06
    щается
    0.06
     توانید
    0.06
    十六
    0.06
    Withdraw
    0.06
    Act Density 0.004%

    No Known Activations