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

    Neuronpedia

    INDEX
    Explanations

    learn shape size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ceph
    0.66
     elevated
    0.66
     আহম্মদ
    0.64
     upper
    0.64
     Fl
    0.64
    achers
    0.63
     pedig
    0.63
    ond
    0.63
    fl
    0.63
     need
    0.62
    POSITIVE LOGITS
    createSprite
    0.86
    Ꮖ
    0.77
    Dijstra
    0.68
     Voiture
    0.66
    圄
    0.65
     createSprite
    0.65
     পারস্প
    0.65
     මෙ
    0.64
    жном
    0.62
    ፊት
    0.62
    Act Density 0.032%

    No Known Activations