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

    Neuronpedia

    INDEX
    Explanations

    weit entfernt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Encript
    0.40
    aan
    0.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.36
    Fl
    0.36
    آ
    0.36
    Gonz
    0.35
    سي
    0.35
    occan
    0.35
     GIF
    0.35
     CNRS
    0.35
    POSITIVE LOGITS
    ಹೆ
    0.38
     fuses
    0.35
     reduces
    0.35
     cleverly
    0.34
     feb
    0.34
     fuse
    0.34
     Stern
    0.34
     Boyd
    0.34
     auft
    0.34
     ছেলেরা
    0.33
    Act Density 0.000%

    No Known Activations