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

    Neuronpedia

    INDEX
    Explanations

    internal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (blog
    -0.07
     منظور
    -0.07
     Spoon
    -0.07
     Seed
    -0.07
    classify
    -0.06
     Cheers
    -0.06
     recursion
    -0.06
    创
    -0.06
     frustrating
    -0.06
    oste
    -0.06
    POSITIVE LOGITS
     internal
    0.08
     ],↵
    0.07
    vertime
    0.06
     Internal
    0.06
     counseling
    0.06
     ALLOW
    0.06
    INTERNAL
    0.06
    /cpp
    0.06
    ][$
    0.06
    _FIELD
    0.06
    Act Density 0.007%

    No Known Activations