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

    Neuronpedia

    INDEX
    Explanations

    understanding concepts or potential applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     memang
    0.39
    omotive
    0.39
     styling
    0.38
     Fabrics
    0.38
     Reservation
    0.38
    Fill
    0.37
    सव
    0.37
    㠱
    0.37
    isVideoRecording
    0.36
    ین
    0.36
    POSITIVE LOGITS
    សំ
    0.41
     AAA
    0.39
    Ð
    0.38
     avantaj
    0.38
     GCBO
    0.36
    usser
    0.36
     inget
    0.36
    uu
    0.35
    ပျ
    0.35
     BBBB
    0.35
    Act Density 0.001%

    No Known Activations