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

    Neuronpedia

    INDEX
    Explanations

    places and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Auswirkungen
    0.29
     Verhalten
    0.27
     epigen
    0.26
     വ്യക്ത
    0.26
     proposte
    0.26
     Jürgen
    0.25
     açısından
    0.25
     ሁሉም
    0.25
     pengaruh
    0.25
     Yukawa
    0.25
    POSITIVE LOGITS
    RI
    0.27
    Park
    0.25
    國
    0.24
    LE
    0.24
    오
    0.24
    ION
    0.23
    לי
    0.23
    ту
    0.23
    수
    0.23
    德
    0.23
    Act Density 0.075%

    No Known Activations