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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     axis
    -0.07
    ัน
    -0.06
     цик
    -0.06
    }',
    -0.06
    券
    -0.06
     khiến
    -0.06
     output
    -0.06
     最
    -0.06
    iais
    -0.06
     shameful
    -0.06
    POSITIVE LOGITS
    _DECL
    0.07
     Conscious
    0.06
     accession
    0.06
          
    0.06
     Wow
    0.06
    LOB
    0.06
    .prot
    0.06
     Charleston
    0.06
     αξ
    0.06
    571
    0.06
    Act Density 0.000%

    No Known Activations