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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Однак
    -0.07
    umbnails
    -0.07
    ्मन
    -0.07
     UserManager
    -0.07
     buy
    -0.06
     οποίο
    -0.06
     reserve
    -0.06
    लब
    -0.06
     balık
    -0.06
     CI
    -0.06
    POSITIVE LOGITS
     passé
    0.07
    เวล
    0.06
    (trigger
    0.06
     พฤษภาคม
    0.06
    Pattern
    0.06
     ‎
    0.06
    ^
    0.06
     disillusion
    0.06
    ='${
    0.06
     elektron
    0.06
    Act Density 0.018%

    No Known Activations