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

    Neuronpedia

    INDEX
    Explanations

    im

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Suffolk
    -0.07
    ｣
    -0.07
    ')}}
    -0.07
     MacDonald
    -0.07
     Snowden
    -0.06
     }}
↵
    -0.06
    undles
    -0.06
    �
    -0.06
    ,))↵
    -0.06
    ">
↵
↵
    -0.06
    POSITIVE LOGITS
    译
    0.07
    ={(
    0.07
     reim
    0.07
    -cert
    0.07
     fencing
    0.06
    issor
    0.06
     earrings
    0.06
    раз
    0.06
     kim
    0.06
    _Variable
    0.06
    Act Density 0.579%

    No Known Activations