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

    Neuronpedia

    INDEX
    Explanations

    approvals and permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உண
    0.42
    reli
    0.38
     defocus
    0.38
     insoluble
    0.37
     croissants
    0.37
     উপলব্ধি
    0.36
    ান্তর
    0.36
    搠
    0.36
    Translatef
    0.35
    ពិស
    0.35
    POSITIVE LOGITS
     approval
    3.83
    approval
    3.47
     Approval
    3.45
    Approval
    3.36
     approvals
    3.30
     approve
    3.20
     aprobación
    3.02
     approved
    2.95
     approves
    2.95
     approving
    2.86
    Act Density 0.094%

    No Known Activations