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

    Neuronpedia

    INDEX
    Explanations

    Gemma team

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of the model's name/brand (the token identifying the model).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
     as
    1.48
    are
    1.09
    ва
    1.04
    have
    1.02
    ores
    1.00
    จะ
    0.96
     with
    0.92
     on
    0.91
     have
    0.91
    க்
    0.90
    POSITIVE LOGITS
    L
    1.37
    H
    1.25
    F
    1.17
    M
    1.12
    B
    1.08
    Emily
    1.05
    S
    1.05
    Sarah
    1.02
    in
    1.00
    K
    1.00
    Act Density 0.028%

    No Known Activations