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

    Neuronpedia

    INDEX
    Explanations

    lift

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invites
    -0.08
     EDGE
    -0.08
     Cinder
    -0.08
     floppy
    -0.07
     misses
    -0.07
     annunci
    -0.07
     Nvidia
    -0.07
     CCS
    -0.07
     compress
    -0.07
    ICENSE
    -0.07
    POSITIVE LOGITS
    حوال
    0.08
    但实际上
    0.07
     самым
    0.07
    .ToBoolean
    0.07
    iomanip
    0.07
     возмож
    0.07
    到底
    0.07
     metals
    0.07
    ed
    0.07
    🧐
    0.06
    Act Density 0.001%

    No Known Activations