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

    Neuronpedia

    INDEX
    Explanations

    academic paper structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '|
    -0.07
     Pir
    -0.06
     suicidal
    -0.06
     biking
    -0.06
     brom
    -0.06
     Vall
    -0.06
    -dollar
    -0.06
    Providers
    -0.06
    Planning
    -0.06
    \Helper
    -0.06
    POSITIVE LOGITS
    回答
    0.07
    _GB
    0.06
     पहल
    0.06
    =`
    0.06
    \model
    0.06
    星期
    0.06
    .:.:.:.:
    0.06
     보내
    0.06
     İstanbul
    0.06
    _pb
    0.06
    Act Density 0.018%

    No Known Activations