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
     EXCEPTION
    -0.07
     sin
    -0.07
     Shell
    -0.07
     Sec
    -0.07
    穴
    -0.07
     ()↵
    -0.07
    ().'
    -0.06
     FU
    -0.06
    ippets
    -0.06
     masc
    -0.06
    POSITIVE LOGITS
    州
    0.07
    תחרות
    0.07
    חזור
    0.07
     backyard
    0.07
    剖析
    0.07
     stands
    0.06
    提振
    0.06
    illisecond
    0.06
    reatment
    0.06
    _week
    0.06
    Act Density 0.001%

    No Known Activations