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

    Neuronpedia

    INDEX
    Explanations

    passive voice constructions and mentions of sports

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

    Follows first-person pronouns

    np_acts-logits-general · gemini-2.0-flash

    We are; You know; To play

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (!__
    -0.67
     nemlig
    -0.60
    のです
    -0.57
    のですね
    -0.55
    =_
    -0.53
    featureID
    -0.52
     hitherto
    -0.52
    Meanwhile
    -0.52
     Meanwhile
    -0.51
     carré
    -0.51
    POSITIVE LOGITS
     fortunate
    0.61
    ortunadamente
    0.55
     AssemblyCulture
    0.54
    enderror
    0.54
     obviamente
    0.53
    horabuena
    0.52
     bezeichneter
    0.51
    僕
    0.50
     AspNetCore
    0.50
    envie
    0.49
    Act Density 0.132%

    No Known Activations