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

    Neuronpedia

    INDEX
    Explanations

    */ and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     demeanor
    -0.08
     honest
    -0.07
    的朋友
    -0.07
     Maintain
    -0.07
    rolls
    -0.07
    _expected
    -0.07
    .stat
    -0.07
    /i
    -0.07
    dda
    -0.07
     PP
    -0.07
    POSITIVE LOGITS
    技法
    0.07
    �
    0.07
    oomla
    0.07
    iral
    0.07
    צפייה
    0.07
     Респуб
    0.06
    (DBG
    0.06
     xlink
    0.06
    =view
    0.06
    __("
    0.06
    Act Density 0.026%

    No Known Activations