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

    Neuronpedia

    INDEX
    Explanations

    academic journals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    枌
    0.48
    Tabpage
    0.46
    棦
    0.45
     pokemon
    0.44
    iktok
    0.44
     стаўкі
    0.44
    Dragging
    0.44
    🫰
    0.44
     Oogie
    0.44
    ొప్పి
    0.43
    POSITIVE LOGITS
     Journal
    1.76
    Journal
    1.66
     journal
    1.59
    journal
    1.36
     JOURNAL
    1.34
     journals
    1.29
     Zeitschrift
    1.24
     जर्नल
    1.11
    ournal
    1.09
    journals
    1.08
    Act Density 0.012%

    No Known Activations