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

    Neuronpedia

    INDEX
    Explanations

    Sentence starters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itone
    -0.07
     races
    -0.07
    Cart
    -0.06
     mechanism
    -0.06
    OCI
    -0.06
     BufferedWriter
    -0.06
    ich
    -0.06
     artists
    -0.06
     TC
    -0.06
    urse
    -0.06
    POSITIVE LOGITS
    ائمة
    0.07
    ','.
    0.07
     GUILayout
    0.07
    (predicate
    0.07
     наличи
    0.07
    ',['../
    0.06
    ではなく
    0.06
    earning
    0.06
     그냥
    0.06
     đáp
    0.06
    Act Density 0.274%

    No Known Activations