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

    Neuronpedia

    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Epoch
    -0.07
    69
    -0.07
     бер
    -0.06
    .Word
    -0.06
     lashes
    -0.06
     words
    -0.06
    ๋
    -0.06
    AVE
    -0.06
    869
    -0.06
     profess
    -0.06
    POSITIVE LOGITS
     PSA
    0.06
     insan
    0.06
    ไหน
    0.06
    ()},
    0.06
    -important
    0.06
     اعلام
    0.06
     иг
    0.06
    发行
    0.06
     startling
    0.06
     redis
    0.06
    Act Density 0.021%

    No Known Activations