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

    Neuronpedia

    INDEX
    Explanations

    different kinds and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     homebuyers
    0.54
     babies
    0.53
     woman
    0.50
     bebés
    0.50
     skiers
    0.50
     teenagers
    0.49
     bedrijven
    0.48
     infants
    0.47
     entreprises
    0.47
     toddlers
    0.47
    POSITIVE LOGITS
     approaches
    0.53
     definitions
    0.52
     Interpret
    0.51
     interpr
    0.51
     Approach
    0.50
    Interpretation
    0.50
     interpretations
    0.49
    Use
    0.48
    interpret
    0.48
     Interpretation
    0.48
    Act Density 0.002%

    No Known Activations