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

    Neuronpedia

    INDEX
    Explanations

    concepts for an audience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     begon
    0.55
    anium
    0.49
     Kasım
    0.48
     byg
    0.47
    ੱਖ
    0.46
     τὸν
    0.46
    ਈ
    0.46
     wygl
    0.46
    🅘
    0.46
     rake
    0.45
    POSITIVE LOGITS
     {
    0.45
     галу
    0.44
    άν
    0.42
    ানে
    0.42
     avoided
    0.41
     ين
    0.40
    는
    0.40
     య
    0.39
    管理者
    0.39
    are
    0.39
    Act Density 0.005%

    No Known Activations