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

    Neuronpedia

    INDEX
    Explanations

    pattern format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    질
    -0.08
    784
    -0.07
    _FC
    -0.07
     fc
    -0.07
    	exp
    -0.06
    ancel
    -0.06
     Verg
    -0.06
     Wizard
    -0.06
     ты
    -0.06
    UIT
    -0.06
    POSITIVE LOGITS
    +]
    0.07
    (@"%@",
    0.07
     Venus
    0.07
     outsiders
    0.07
    MO
    0.06
     Caller
    0.06
    Choices
    0.06
    VMLINUX
    0.06
     />
↵
    0.06
    لیس
    0.06
    Act Density 0.006%

    No Known Activations