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

    Neuronpedia

    INDEX
    Explanations

    Code and/or punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.07
    azo
    -0.07
     المه
    -0.07
     buses
    -0.07
    =row
    -0.06
     Wahl
    -0.06
    ец
    -0.06
    fillable
    -0.06
    Tracks
    -0.06
    ould
    -0.06
    POSITIVE LOGITS
     ettir
    0.06
     domina
    0.06
    �
    0.06
     amid
    0.06
    	system
    0.05
    sorting
    0.05
     allocated
    0.05
     bub
    0.05
    isz
    0.05
    人民共和国
    0.05
    Act Density 0.054%

    No Known Activations