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

    Neuronpedia

    INDEX
    Explanations

    numbers and slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mindless
    0.18
     crispy
    0.17
     توڑ
    0.17
     bushy
    0.17
     slags
    0.17
     Darstellung
    0.16
     دیے
    0.16
     mocker
    0.16
     slits
    0.16
     grasping
    0.16
    POSITIVE LOGITS
    ↵
    0.28
    .
    0.28
    _
    0.24
    uk
    0.24
    us
    0.23
    ior
    0.23
    ua
    0.22
    ud
    0.22
    yn
    0.22
    ist
    0.21
    Act Density 0.345%

    No Known Activations