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

    Neuronpedia

    INDEX
    Explanations

    depth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    리스
    -0.07
     White
    -0.07
    finger
    -0.06
     jednot
    -0.06
    ADF
    -0.06
     recreation
    -0.06
    etto
    -0.06
     Dre
    -0.06
     Acer
    -0.06
    _INSERT
    -0.06
    POSITIVE LOGITS
     methods
    0.07
     examining
    0.07
     snatch
    0.07
     examined
    0.06
    _requirements
    0.06
     appro
    0.06
     techniques
    0.06
     explored
    0.06
     substantive
    0.06
     methodologies
    0.06
    Act Density 0.018%

    No Known Activations