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

    Neuronpedia

    INDEX
    Explanations

    confined

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ativ
    -0.24
    .Spring
    -0.24
    æľĭ
    -0.24
     cone
    -0.24
    uming
    -0.24
    ogn
    -0.23
    itational
    -0.23
    centre
    -0.23
     represent
    -0.23
    atables
    -0.23
    POSITIVE LOGITS
    orney
    0.28
     CCD
    0.28
    FUL
    0.26
    ħ§
    0.25
     Sergei
    0.25
    erge
    0.25
    èľķ
    0.25
    æĹ¥æĻļ
    0.25
    ych
    0.25
    è··
    0.25
    Act Density 0.005%

    No Known Activations