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

    Neuronpedia

    INDEX
    Explanations

    specific examples and their contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     használ
    0.39
     henne
    0.39
     když
    0.38
     häufig
    0.37
     nummer
    0.36
    عند
    0.36
     wenn
    0.36
     când
    0.36
     fermeture
    0.36
     již
    0.36
    POSITIVE LOGITS
    とその
    0.44
    provides
    0.38
    及其
    0.37
    essentially
    0.35
     фаразлау
    0.34
    implies
    0.33
    provide
    0.31
    함으로써
    0.31
    ,(
    0.31
    including
    0.30
    Act Density 0.144%

    No Known Activations