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

    Neuronpedia

    INDEX
    Explanations

    describing or explaining something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rekli
    0.40
     milled
    0.40
    र्मा
    0.39
     inconvenience
    0.39
     suble
    0.38
    ardia
    0.37
    mainly
    0.37
     streetwear
    0.37
     herald
    0.36
    uggish
    0.36
    POSITIVE LOGITS
     Yuk
    0.42
     Yoga
    0.40
     JOY
    0.40
     Wash
    0.38
     SDK
    0.37
     않았다
    0.37
    博物馆
    0.37
    FindingsResponse
    0.37
    Yoga
    0.37
     Joy
    0.37
    Act Density 0.000%

    No Known Activations