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

    Neuronpedia

    INDEX
    Explanations

    ideal for specific tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ls
    0.54
    bl
    0.50
    Num
    0.50
    names
    0.49
    sal
    0.47
    reiro
    0.46
    RELEASE
    0.46
    iful
    0.44
    as
    0.43
    RIGHT
    0.43
    POSITIVE LOGITS
     ため
    0.55
     빨리
    0.53
     boardroom
    0.52
     원
    0.50
     wear
    0.50
    от
    0.49
     runny
    0.49
     invade
    0.48
    いる
    0.48
     unwittingly
    0.48
    Act Density 0.000%

    No Known Activations