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

    Neuronpedia

    INDEX
    Explanations

    delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bin
    -0.07
     reachable
    -0.07
    639
    -0.06
    ULATE
    -0.06
    ,+
    -0.06
     Ş
    -0.06
     hiding
    -0.06
     "=
    -0.06
     HIT
    -0.06
     axis
    -0.06
    POSITIVE LOGITS
    myModalLabel
    0.07
    Anyway
    0.07
    -android
    0.06
     obnov
    0.06
    .BASE
    0.06
    xAE
    0.06
     herkes
    0.06
    AdapterManager
    0.06
     marvel
    0.06
    _FAULT
    0.06
    Act Density 0.018%

    No Known Activations