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

    Neuronpedia

    INDEX
    Explanations

    Bugs Bunny, Bug's Life, bug tracking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizing
    0.40
    чев
    0.39
    arb
    0.38
    Testing
    0.38
    Johnny
    0.38
    hacking
    0.37
    pip
    0.36
    失
    0.35
    Github
    0.35
    Pip
    0.35
    POSITIVE LOGITS
     metri
    0.50
     wage
    0.44
     愛
    0.43
     Life
    0.43
     superst
    0.43
     zari
    0.41
     endowment
    0.41
     toer
    0.41
    ាន
    0.39
     paraf
    0.39
    Act Density 0.001%

    No Known Activations