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

    Neuronpedia

    INDEX
    Explanations

    .webp, .pts, .app, .html

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     All
    0.45
     Break
    0.38
    щі
    0.38
    น์โหลด
    0.36
     Ex
    0.35
    eki
    0.35
    All
    0.35
     Marx
    0.34
    oshop
    0.34
    丿
    0.34
    POSITIVE LOGITS
     titration
    0.44
    bigvee
    0.42
     stenosis
    0.38
     статья
    0.38
     loudspeaker
    0.37
     Pentec
    0.37
     trope
    0.37
    .".,
    0.37
    ципа
    0.37
    ethoscope
    0.37
    Act Density 0.009%

    No Known Activations