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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Focus
    -0.07
    ][_
    -0.07
    flater
    -0.07
     Capacity
    -0.07
    "name
    -0.07
     Michaels
    -0.07
    .kr
    -0.06
    thren
    -0.06
    elsen
    -0.06
    .ant
    -0.06
    POSITIVE LOGITS
    celed
    0.07
    ikal
    0.07
    _photo
    0.06
     hypoth
    0.06
     Б
    0.06
    _hresult
    0.06
    گری
    0.06
    _SMS
    0.06
    ,’
    0.06
    }}],↵
    0.06
    Act Density 0.007%

    No Known Activations