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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    个月内
    -0.07
    .PathVariable
    -0.07
    (info
    -0.07
     милли
    -0.07
     Juli
    -0.07
    Permissions
    -0.07
     Bach
    -0.06
     Populate
    -0.06
    㺄
    -0.06
    汇聚
    -0.06
    POSITIVE LOGITS
    rots
    0.08
    roys
    0.07
    /access
    0.07
    Injected
    0.07
    Hero
    0.07
     docking
    0.07
    _cmos
    0.07
    _journal
    0.07
    	statement
    0.07
    듣
    0.07
    Act Density 0.007%

    No Known Activations