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

    Neuronpedia

    INDEX
    Explanations

    emissions targets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     timing
    -0.08
    Timing
    -0.08
     Timing
    -0.07
     raken
    -0.07
    keypress
    -0.07
     कौन
    -0.07
     shiny
    -0.07
     సంద
    -0.07
     edge
    -0.07
     indefinite
    -0.07
    POSITIVE LOGITS
    .previous
    0.12
     sebelumnya
    0.11
    _previous
    0.11
    198
    0.11
     предыдущ
    0.11
    Previous
    0.11
     eerdere
    0.11
    previous
    0.10
    去年
    0.10
    _last
    0.10
    Act Density 0.013%

    No Known Activations