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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "+
    -0.07
     tightly
    -0.06
     GOLD
    -0.06
    isors
    -0.06
     striker
    -0.06
     favourable
    -0.06
     ferm
    -0.06
    ités
    -0.06
    merchant
    -0.06
     other
    -0.06
    POSITIVE LOGITS
     Correspond
    0.07
     Toledo
    0.06
     Moody
    0.06
    هنگ
    0.06
     Verify
    0.06
    нообраз
    0.06
    ederland
    0.06
     mr
    0.06
     Bankası
    0.06
    ihad
    0.06
    Act Density 0.007%

    No Known Activations