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

    Neuronpedia

    INDEX
    Explanations

    rend

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     delightful
    -0.07
    див
    -0.06
     shields
    -0.06
     Composite
    -0.06
     Wonder
    -0.06
     debates
    -0.06
     caves
    -0.06
    ERC
    -0.06
    228
    -0.06
    _table
    -0.06
    POSITIVE LOGITS
    ुकस
    0.07
    шей
    0.06
    _people
    0.06
     momentum
    0.06
     hä
    0.06
     Moms
    0.06
     mog
    0.06
     Macros
    0.06
    >>↵↵
    0.06
    grown
    0.06
    Act Density 0.003%

    No Known Activations