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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remin
    -0.07
     pon
    -0.07
    area
    -0.07
     woods
    -0.07
     والد
    -0.06
    wang
    -0.06
     primaries
    -0.06
    �
    -0.06
     كان
    -0.06
     Falls
    -0.06
    POSITIVE LOGITS
    _certificate
    0.06
    .apply
    0.06
    mobx
    0.06
     spielen
    0.06
    .gsub
    0.06
    Chinese
    0.06
    (search
    0.06
    确认
    0.06
    inston
    0.06
     insisting
    0.05
    Act Density 0.007%

    No Known Activations