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

    Neuronpedia

    INDEX
    Explanations

    body parts/locations/fields

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frame
    -0.56
    frame
    -0.54
     dentaire
    -0.53
     frames
    -0.52
     EnglishChoose
    -0.51
     TECN
    -0.50
     télévis
    -0.50
    IUrlHelper
    -0.49
     Frame
    -0.49
     ListNode
    -0.48
    POSITIVE LOGITS
    zyż
    0.51
     Britannia
    0.51
     sceptre
    0.50
    salms
    0.49
    řad
    0.48
    TagMode
    0.48
    ArgsConstructor
    0.48
    جغرافيا
    0.47
     Mahal
    0.47
     Churchill
    0.46
    Act Density 0.012%

    No Known Activations