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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Charges
    -0.07
    fad
    -0.06
    يلاد
    -0.06
     Gal
    -0.06
     eines
    -0.06
    .two
    -0.06
    losti
    -0.06
    arges
    -0.06
     snapshots
    -0.06
    (al
    -0.06
    POSITIVE LOGITS
    ENGINE
    0.07
    Que
    0.07
     expressing
    0.07
     their
    0.06
     производства
    0.06
    所属
    0.06
     his
    0.06
     Guests
    0.06
     Mechanics
    0.06
    녕
    0.06
    Act Density 0.007%

    No Known Activations