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

    Neuronpedia

    INDEX
    Explanations

    to [action verb]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sniping
    0.34
     validation
    0.34
     mockery
    0.33
     validations
    0.33
     poaching
    0.32
     provisioning
    0.32
     distancing
    0.32
     routing
    0.31
     chiar
    0.31
     onboarding
    0.31
    POSITIVE LOGITS
     take
    0.44
     make
    0.41
     put
    0.39
     do
    0.37
     use
    0.36
     organize
    0.36
     eat
    0.36
     develop
    0.36
     provide
    0.36
     go
    0.35
    Act Density 0.123%

    No Known Activations