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

    Neuronpedia

    INDEX
    Explanations

    750

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sebastian
    -0.07
     Fate
    -0.07
     vow
    -0.07
     adaptation
    -0.07
    ificação
    -0.07
    ：%
    -0.07
     Switch
    -0.07
    .text
    -0.07
     resposta
    -0.07
     fasta
    -0.06
    POSITIVE LOGITS
    750
    0.12
    75
    0.11
    250
    0.10
    375
    0.10
    751
    0.09
    125
    0.09
    550
    0.08
    650
    0.08
    350
    0.08
     sidewalk
    0.07
    Act Density 0.054%

    No Known Activations