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

    Neuronpedia

    INDEX
    Explanations

    Community Standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FedEx
    0.62
    𝗠
    0.55
    𝗖
    0.53
    𝐌
    0.53
     bệnh
    0.52
    Ⴊ
    0.52
     Zumba
    0.52
    𝙻
    0.51
    𝗟
    0.51
    𝗽
    0.50
    POSITIVE LOGITS
    ivil
    0.54
    inosaur
    0.54
    ieg
    0.51
    ital
    0.50
    iverse
    0.49
    om
    0.49
    u
    0.49
    inos
    0.48
    uid
    0.48
     enn
    0.48
    Act Density 0.001%

    No Known Activations