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

    Neuronpedia

    INDEX
    Explanations

    Location Matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asesin
    0.50
    iegen
    0.47
     leaflets
    0.46
     inhibits
    0.46
     stems
    0.45
     윤
    0.44
    Bindings
    0.44
     追加
    0.44
     丨
    0.44
    ontrol
    0.43
    POSITIVE LOGITS
    D
    0.55
    j
    0.50
    R
    0.49
    e
    0.48
     your
    0.47
    麃
    0.46
    i
    0.45
     heck
    0.45
    ooo
    0.45
    horse
    0.44
    Act Density 0.000%

    No Known Activations