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

    Neuronpedia

    INDEX
    Explanations

    \Console

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inadvertently
    -0.07
     Huang
    -0.06
    _thickness
    -0.06
    .le
    -0.06
     GameController
    -0.06
     因
    -0.06
    Mode
    -0.06
    CARD
    -0.06
    containers
    -0.06
     mue
    -0.06
    POSITIVE LOGITS
     zmq
    0.09
     Sequential
    0.07
     critically
    0.07
    동
    0.07
    irates
    0.07
     lonely
    0.06
     ],↵
    0.06
    unter
    0.06
     opposite
    0.06
    -Z
    0.06
    Act Density 0.001%

    No Known Activations