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

    Neuronpedia

    INDEX
    Explanations

    Poland

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arendra
    -0.07
    -edge
    -0.06
     conver
    -0.06
     peaks
    -0.06
     XI
    -0.06
     MJ
    -0.06
    vertise
    -0.06
    ampus
    -0.06
    nutím
    -0.06
    [v
    -0.06
    POSITIVE LOGITS
     exagger
    0.07
     진짜
    0.06
     Equal
    0.06
     maxlength
    0.06
     errorThrown
    0.06
    สถานท
    0.06
     QText
    0.06
     tweets
    0.06
     UILabel
    0.06
    Fight
    0.06
    Act Density 0.005%

    No Known Activations