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

    Neuronpedia

    INDEX
    Explanations

    loops and obligations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    尔
    0.63
     обучения
    0.58
    ップ
    0.56
    л
    0.56
    ির
    0.54
    TTS
    0.54
     زيادة
    0.53
    Collide
    0.53
     большинство
    0.51
    ILLS
    0.50
    POSITIVE LOGITS
     dining
    0.65
    tering
    0.61
    teres
    0.58
     veranda
    0.58
     courthouse
    0.56
    tere
    0.55
    fighters
    0.55
    dining
    0.55
     homely
    0.54
    np
    0.54
    Act Density 0.000%

    No Known Activations