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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ves
    -0.07
    _go
    -0.07
    eren
    -0.06
     Salv
    -0.06
     bil
    -0.06
     close
    -0.06
     bases
    -0.06
    oč
    -0.06
     utiliz
    -0.06
    umpy
    -0.06
    POSITIVE LOGITS
    �
    0.07
    _refs
    0.06
    nač
    0.06
    ptype
    0.06
     ASCII
    0.06
     오늘
    0.06
     tấm
    0.06
     erotiske
    0.06
     افراد
    0.06
     htonl
    0.06
    Act Density 0.044%

    No Known Activations