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

    Neuronpedia

    INDEX
    Explanations

    Code and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    床
    -0.06
    �
    -0.06
     UNIT
    -0.06
    RunLoop
    -0.06
    ým
    -0.06
    棚
    -0.05
    à
    -0.05
    anya
    -0.05
     takdir
    -0.05
    іє
    -0.05
    POSITIVE LOGITS
     AVG
    0.07
    .embed
    0.07
    -eight
    0.07
    �能
    0.07
    marginLeft
    0.07
    ायन
    0.07
    征
    0.07
     berth
    0.07
    ommen
    0.07
    _NEAREST
    0.06
    Act Density 0.060%

    No Known Activations