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
     mute
    -0.07
    (src
    -0.06
     Jail
    -0.06
    (p
    -0.06
    (argv
    -0.06
    .Store
    -0.06
     respectively
    -0.06
    限制
    -0.06
    	struct
    -0.06
    급
    -0.06
    POSITIVE LOGITS
    配
    0.07
     recep
    0.07
    .Parameter
    0.06
     Louis
    0.06
    soever
    0.06
     Umb
    0.06
    .M
    0.06
     başlat
    0.06
    \App
    0.06
    .selected
    0.06
    Act Density 0.008%

    No Known Activations