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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prototypes
    -0.07
     Prototype
    -0.06
    	Integer
    -0.06
     unfolding
    -0.06
     undocumented
    -0.06
     incoming
    -0.06
     contemplated
    -0.06
     intimacy
    -0.06
    Area
    -0.06
    ))).
    -0.06
    POSITIVE LOGITS
    浜
    0.07
    řen
    0.07
    择
    0.07
     encuentra
    0.06
     Β
    0.06
    存档
    0.06
     Bett
    0.06
    ird
    0.06
     مرکزی
    0.06
    افية
    0.06
    Act Density 0.009%

    No Known Activations