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
    livě
    -0.06
    agnostic
    -0.06
    Finished
    -0.06
    ागत
    -0.06
    yling
    -0.06
    IMIT
    -0.06
    esture
    -0.06
    imity
    -0.06
     tới
    -0.06
    radu
    -0.06
    POSITIVE LOGITS
     Cannon
    0.07
     precedence
    0.07
    кус
    0.07
     convicted
    0.06
     Stephan
    0.06
     ”↵
    0.06
     Exxon
    0.06
     basket
    0.06
    ัต
    0.06
     promoted
    0.06
    Act Density 0.006%

    No Known Activations