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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATEGY
    -0.06
    енс
    -0.06
    izzlies
    -0.06
    _dw
    -0.06
    _HEAP
    -0.06
    (weight
    -0.06
     verm
    -0.06
     timeouts
    -0.06
    alat
    -0.06
    _LINES
    -0.05
    POSITIVE LOGITS
     siempre
    0.07
     Norse
    0.07
     Opinion
    0.06
     Progress
    0.06
     claiming
    0.06
     NPCs
    0.06
    Ế
    0.06
    Installed
    0.06
    erland
    0.06
    .ContextCompat
    0.06
    Act Density 0.011%

    No Known Activations