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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '/')
    -0.06
    ึ
    -0.06
    (period
    -0.06
    ().↵
    -0.06
     bailout
    -0.06
    Location
    -0.06
     �
    -0.05
     Erin
    -0.05
     deltas
    -0.05
     sam
    -0.05
    POSITIVE LOGITS
     Poster
    0.07
    anooga
    0.07
    ژن
    0.07
     contribute
    0.07
    еними
    0.07
    Runner
    0.07
     hạng
    0.07
     Advent
    0.07
     Knee
    0.06
     تأثیر
    0.06
    Act Density 0.003%

    No Known Activations