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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    回答
    -0.07
    <Menu
    -0.06
    (accounts
    -0.06
     벌
    -0.06
    ani
    -0.06
    logue
    -0.06
     �
    -0.06
     timer
    -0.06
    /read
    -0.06
    ParameterValue
    -0.06
    POSITIVE LOGITS
     (<
    0.06
     gorgeous
    0.06
    overs
    0.06
     phenomenal
    0.06
    /sm
    0.06
    兒
    0.06
    bard
    0.06
     subgroup
    0.06
    وا
    0.06
    ohan
    0.06
    Act Density 0.016%

    No Known Activations