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

    Neuronpedia

    INDEX
    Explanations

    servo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ira
    -0.62
    ls
    -0.61
    rey
    -0.59
     the
    -0.57
    rit
    -0.55
     a
    -0.54
     such
    -0.52
     similar
    -0.50
     common
    -0.49
    lix
    -0.47
    POSITIVE LOGITS
    o
    0.94
     تانيه
    0.88
    y
    0.88
    otry
    0.88
     useRouter
    0.85
    ^(@)
    0.85
    ✨:
    0.84
     Majefty
    0.84
     myſelf
    0.84
     Anſ
    0.83
    Act Density 0.294%

    No Known Activations