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

    Neuronpedia

    INDEX
    Explanations

    cos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    attie
    -0.08
     排
    -0.07
     Accountability
    -0.07
    /train
    -0.07
    /input
    -0.07
     auf
    -0.07
     Completion
    -0.07
     Steward
    -0.07
    ોની
    -0.07
    /support
    -0.07
    POSITIVE LOGITS
     ýerde
    0.08
    రోనా
    0.08
     хона
    0.08
     কিংবা
    0.08
    .static
    0.08
     ataupun
    0.08
    ிருக்க
    0.08
    .unit
    0.08
     método
    0.08
     карда
    0.08
    Act Density 0.012%

    No Known Activations