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

    Neuronpedia

    INDEX
    Explanations

    management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .While
    -0.06
     Su
    -0.06
     Impl
    -0.06
    /constants
    -0.06
    Yet
    -0.06
    .Initialize
    -0.06
    _draft
    -0.06
    aks
    -0.06
     Knife
    -0.06
    CPU
    -0.06
    POSITIVE LOGITS
     surg
    0.07
    ้อย
    0.07
     fours
    0.07
    earer
    0.07
    είτε
    0.07
     MISSING
    0.07
     SOUR
    0.06
     FITNESS
    0.06
     )))
    0.06
     न
    0.06
    Act Density 0.082%

    No Known Activations