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

    Neuronpedia

    INDEX
    Explanations

    markers indicating significant changes or events

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

    Text after em dashes or dashes

    np_acts-logits-general · gemini-2.0-flash

    written, you, all, Shoot, Norman, Phase, Hampshire, Updating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.66
     --
    -0.63
    .....
    -0.58
    ......
    -0.58
    ....
    -0.54
    .......
    -0.53
     .....
    -0.53
    ,....
    -0.52
     ...
    -0.51
     ......
    -0.49
    POSITIVE LOGITS
    hence
    0.94
     hence
    0.90
     это
    0.89
    especially
    0.88
    albeit
    0.86
    although
    0.86
     albeit
    0.85
    including
    0.85
    ----------------
    0.85
    namely
    0.84
    Act Density 0.260%

    No Known Activations