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

    Neuronpedia

    INDEX
    Explanations

    Discussions and opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     영어
    -0.07
    lld
    -0.06
    -0.06
     factual
    -0.06
     ||↵
    -0.06
      	↵
    -0.06
    .DataGridViewContentAlignment
    -0.06
    ीं,
    -0.06
    ことに
    -0.06
    563
    -0.06
    POSITIVE LOGITS
     зд
    0.08
    _rep
    0.07
     sofort
    0.07
     injecting
    0.07
     акку
    0.07
     neden
    0.07
    št
    0.07
    (Temp
    0.07
     emit
    0.06
    'acc
    0.06
    Act Density 0.272%

    No Known Activations