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

    Neuronpedia

    INDEX
    Explanations

    specific topic queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     τὴν
    0.38
    Ἠ
    0.37
    MVCProject
    0.36
    കളിൽ
    0.35
    第一個
    0.35
    idE
    0.35
    郓
    0.35
    Ἱ
    0.34
     أَ
    0.34
    CFBundle
    0.34
    POSITIVE LOGITS
    ৭
    0.50
    ↵
    0.46
    ні
    0.45
    5
    0.45
    kan
    0.44
    amento
    0.43
    ang
    0.43
    7
    0.43
     maju
    0.42
    will
    0.42
    Act Density 2.155%

    No Known Activations