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

    Neuronpedia

    INDEX
    Explanations

    pushing limits and boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tap
    0.41
     Drop
    0.39
    kten
    0.38
     Assume
    0.37
     साध
    0.37
     MyBatis
    0.37
     Cannot
    0.36
     Microwave
    0.36
    Perry
    0.36
    基本的
    0.36
    POSITIVE LOGITS
     pushing
    1.54
     push
    1.53
     pushed
    1.53
     pushes
    1.46
    Push
    1.45
    push
    1.38
     Push
    1.33
     đẩy
    1.27
    PUSH
    1.27
    推
    1.26
    Act Density 0.013%

    No Known Activations