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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positive evaluations of performance or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    evaluating someone's job

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     per
    -0.31
     leitor
    -0.28
     following
    -0.28
     city
    -0.27
    ${
    -0.27
     directly
    -0.26
    in
    -0.26
    per
    -0.26
    ,
    -0.26
    בות
    -0.25
    POSITIVE LOGITS
    Autoritní
    0.82
     nahilalakip
    0.80
    findpost
    0.72
    ParallelGroup
    0.70
    bootstrapcdn
    0.69
     Congratulations
    0.68
     Autorisations
    0.68
    ContentAsync
    0.68
     ब्रेकडाउन
    0.66
    AnimationsModule
    0.66
    Act Density 0.019%

    No Known Activations