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

    Neuronpedia

    INDEX
    Explanations

    be conveyed, away thy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    R
    0.55
    MDP
    0.53
    இர
    0.52
     debilitating
    0.50
     lowly
    0.50
     enthr
    0.49
    MBA
    0.49
     inexplicable
    0.48
     Bunda
    0.48
    amal
    0.47
    POSITIVE LOGITS
    toFixed
    0.53
     بيانات
    0.51
     побу
    0.51
     повіт
    0.50
     пше
    0.49
    價格
    0.49
    Ｌ
    0.49
    লস
    0.48
    簷
    0.48
     ক
    0.48
    Act Density 0.000%

    No Known Activations