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

    Neuronpedia

    INDEX
    Explanations

    well

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Backup
    -0.07
    idae
    -0.06
     glGet
    -0.06
     […]↵
    -0.06
     Main
    -0.06
     hacer
    -0.06
     시행
    -0.06
    /dat
    -0.06
     herpes
    -0.06
    原来
    -0.06
    POSITIVE LOGITS
    (Pointer
    0.07
    แหน
    0.07
     Batter
    0.07
    _feature
    0.07
     bud
    0.06
    	ll
    0.06
    (artist
    0.06
     Intelli
    0.06
     الدولة
    0.06
    _dense
    0.06
    Act Density 0.015%

    No Known Activations