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

    Neuronpedia

    INDEX
    Explanations

    menu interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     듣
    -0.07
    ､:
    -0.07
    성
    -0.07
    _ij
    -0.06
    acons
    -0.06
     rychle
    -0.06
     Văn
    -0.06
     vascular
    -0.06
     revoke
    -0.06
     있
    -0.06
    POSITIVE LOGITS
     čtyř
    0.07
     daycare
    0.07
    Eff
    0.06
    anded
    0.06
     prohibits
    0.06
    shade
    0.06
    症
    0.06
    Foto
    0.06
     Eff
    0.06
    podob
    0.06
    Act Density 0.050%

    No Known Activations