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

    Neuronpedia

    INDEX
    Explanations

    standard search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dipped
    0.44
     coated
    0.41
    والفق
    0.41
     mould
    0.40
     moulding
    0.39
    ্নি
    0.39
     moulded
    0.39
    mib
    0.39
     रूपये
    0.38
    Stephen
    0.38
    POSITIVE LOGITS
    スム
    0.44
     apologizing
    0.38
    委員
    0.37
    autoprefixer
    0.36
    ?")
    0.36
     adel
    0.35
     hypoth
    0.35
     actitud
    0.35
     assumptions
    0.34
     মহাপ
    0.34
    Act Density 0.000%

    No Known Activations