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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PvP
    -0.07
    .Template
    -0.07
     Maurit
    -0.07
     ви
    -0.07
    _door
    -0.06
    Ur
    -0.06
    Finder
    -0.06
     hãy
    -0.06
    /button
    -0.06
    -it
    -0.06
    POSITIVE LOGITS
    OPY
    0.07
    стич
    0.07
    _MEMORY
    0.07
    的一
    0.06
    kap
    0.06
     foc
    0.06
     steroid
    0.06
    ITCH
    0.06
    多
    0.06
    AMS
    0.06
    Act Density 0.015%

    No Known Activations