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

    Neuronpedia

    INDEX
    Explanations

    block

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뷔
    -0.07
    �
    -0.07
     Lima
    -0.07
    wers
    -0.07
    缶
    -0.07
     consultation
    -0.07
     Украины
    -0.07
    愍
    -0.07
     Chest
    -0.06
    Tex
    -0.06
    POSITIVE LOGITS
    пол
    0.06
    سكان
    0.06
    >s
    0.06
     quello
    0.06
    �
    0.06
    แหล
    0.06
     solidity
    0.06
    rei
    0.06
    units
    0.06
    _UNITS
    0.06
    Act Density 0.004%

    No Known Activations