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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #####↵
    -0.06
    	method
    -0.06
    Kat
    -0.06
     milling
    -0.06
     cooler
    -0.06
    >d
    -0.06
    used
    -0.06
     Mand
    -0.06
    -j
    -0.06
     ignited
    -0.06
    POSITIVE LOGITS
    BE
    0.07
    be
    0.07
    WE
    0.07
    ebe
    0.07
    ube
    0.07
    ween
    0.07
     DIRECTORY
    0.07
    we
    0.06
    SYS
    0.06
     Gore
    0.06
    Act Density 0.008%

    No Known Activations