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

    Neuronpedia

    INDEX
    Explanations

    analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perpetrators
    -0.06
    φα
    -0.06
     Ly
    -0.06
    UPPORT
    -0.06
    _deploy
    -0.06
     จำก
    -0.06
    ICAST
    -0.06
    Stroke
    -0.06
    ergic
    -0.06
    .digest
    -0.06
    POSITIVE LOGITS
    検
    0.07
     statewide
    0.07
     태
    0.07
    칭
    0.07
     penchant
    0.07
     california
    0.07
     Leonardo
    0.06
    +↵↵
    0.06
    GPU
    0.06
    TouchUpInside
    0.06
    Act Density 0.013%

    No Known Activations