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

    Neuronpedia

    INDEX
    Explanations

    play with, play on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    artment
    1.25
    Replacement
    1.21
    CGFloat
    1.19
    एक
    1.16
    Physical
    1.14
    implemented
    1.13
    verbose
    1.11
    Passwords
    1.11
    たとえば
    1.11
    Work
    1.10
    POSITIVE LOGITS
    wright
    1.53
    ধু
    1.28
     havoc
    1.25
     oyn
    1.22
    耍
    1.22
    dough
    1.17
     coy
    1.12
    োয়া
    1.11
    orylation
    1.11
    谑
    1.10
    Act Density 0.067%

    No Known Activations