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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dt
    -0.07
     банк
    -0.06
    oš
    -0.06
    enterprise
    -0.06
    thank
    -0.06
     шк
    -0.06
    õ
    -0.06
    ESS
    -0.06
    875
    -0.06
    yh
    -0.06
    POSITIVE LOGITS
    accine
    0.07
     소리
    0.07
     taste
    0.07
     Career
    0.06
     ]↵↵
    0.06
     enrollment
    0.06
     Taste
    0.06
     amy
    0.06
    Snapshot
    0.06
     Rever
    0.06
    Act Density 0.000%

    No Known Activations