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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    autoreleasepool
    -0.08
     uppercase
    -0.07
    .sign
    -0.07
    Draft
    -0.07
    Scope
    -0.06
     tome
    -0.06
    ocracy
    -0.06
     '?
    -0.06
     Panda
    -0.06
     deem
    -0.06
    POSITIVE LOGITS
     reimburse
    0.07
    ोग
    0.06
     doInBackground
    0.06
     уд
    0.06
    EntityManager
    0.06
     дітей
    0.06
    Uno
    0.06
     delivers
    0.06
     onboard
    0.06
     저장
    0.06
    Act Density 0.004%

    No Known Activations