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

    Neuronpedia

    INDEX
    Explanations

    complex sentences with multiple prepositional phrases and semicolons

    oai_token-act-pair · gemini-2.0-flash

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PKK
    -0.65
     Sarm
    -0.58
     femininas
    -0.57
     Prenez
    -0.57
     becauſe
    -0.55
     Deixe
    -0.54
     Baillargeon
    -0.54
     Inscrivez
    -0.54
     poffible
    -0.54
    PasswordEncoder
    -0.52
    POSITIVE LOGITS
     ra
    0.63
    WriteBarrier
    0.59
     major
    0.54
    Архівовано
    0.52
     just
    0.52
     par
    0.51
     n
    0.51
    namt
    0.51
    rlrl
    0.50
    princ
    0.50
    Act Density 0.683%

    No Known Activations