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

    Neuronpedia

    INDEX
    Explanations

    thinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     S
    -0.07
     IDF
    -0.07
    َس
    -0.06
     L
    -0.06
    -secret
    -0.06
    緊
    -0.06
    alim
    -0.06
     warp
    -0.06
    lep
    -0.06
    obble
    -0.06
    POSITIVE LOGITS
    emouth
    0.07
     وجه
    0.07
     Forum
    0.06
    .PrintWriter
    0.06
     Aerospace
    0.06
    .Timer
    0.06
     Sexy
    0.06
    رفة
    0.06
     Gibson
    0.06
    !.↵↵
    0.06
    Act Density 0.005%

    No Known Activations