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

    Neuronpedia

    INDEX
    Explanations

    scientific species names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     persön
    1.64
    нг
    1.59
    erweise
    1.57
    ab
    1.46
    ERE
    1.43
    та
    1.41
    Doch
    1.34
    ਆ
    1.34
    पणे
    1.33
    EN
    1.32
    POSITIVE LOGITS
    ان
    1.96
    ד
    1.77
    ל
    1.63
     fermions
    1.52
    на
    1.52
    א
    1.51
    ן
    1.50
     espèce
    1.44
     kelamin
    1.44
    ৪
    1.42
    Act Density 0.010%

    No Known Activations