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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    神
    -0.07
    OTT
    -0.07
    感
    -0.07
    .histogram
    -0.07
     diagnosed
    -0.06
    과
    -0.06
     company
    -0.06
    ubuntu
    -0.06
    ooky
    -0.06
    About
    -0.06
    POSITIVE LOGITS
     ор
    0.07
    )")
    0.06
    SURE
    0.06
     Fleet
    0.06
    _nums
    0.06
     سر
    0.06
     }]↵
    0.06
     Ε
    0.06
    ımız
    0.06
     |:
    0.06
    Act Density 0.032%

    No Known Activations