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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (grammarAccess
    -0.06
     sprung
    -0.06
    ('"
    -0.06
     benefiting
    -0.06
    anja
    -0.06
    �
    -0.06
    ("."
    -0.06
    违
    -0.06
     теч
    -0.06
     *@
    -0.06
    POSITIVE LOGITS
    .MULT
    0.08
     transparent
    0.07
    -clean
    0.07
    Bachelor
    0.07
    !")↵↵
    0.07
     Simple
    0.07
    erin
    0.07
    із
    0.07
     변
    0.07
     Load
    0.06
    Act Density 0.000%

    No Known Activations