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

    Neuronpedia

    INDEX
    Explanations

    references to product features and specifications

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

    releasing something

    np_acts-logits-general · gemini-2.0-flash

    release or launch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mergeFrom
    -0.53
    )$}
    -0.53
    velopes
    -0.51
     protoimpl
    -0.51
    ourage
    -0.51
     Blank
    -0.50
    IZEN
    -0.50
     mariée
    -0.49
    ècie
    -0.49
    ecap
    -0.49
    POSITIVE LOGITS
     release
    1.01
     released
    0.88
     Release
    0.87
    release
    0.84
     releases
    0.81
    Release
    0.81
     RELEASE
    0.77
    released
    0.77
     releasing
    0.76
     launch
    0.73
    Act Density 0.186%

    No Known Activations