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

    Neuronpedia

    INDEX
    Explanations

    bring evidence or trouble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hé
    0.48
    ය
    0.46
     nhắn
    0.46
     it
    0.45
     activos
    0.45
     senc
    0.45
     setups
    0.44
     illumin
    0.44
     Fragments
    0.44
    일
    0.43
    POSITIVE LOGITS
    attended
    0.54
    INY
    0.54
     கடுமையான
    0.51
     বলে
    0.47
    era
    0.46
    ça
    0.46
     பார்க்க
    0.46
    form
    0.46
    experienced
    0.46
    泠
    0.46
    Act Density 0.000%

    No Known Activations