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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NC
    -0.07
     tastes
    -0.07
    �
    -0.06
    기의
    -0.06
    ge
    -0.06
     guten
    -0.06
    (note
    -0.06
     pet
    -0.06
    OPLE
    -0.06
     KG
    -0.06
    POSITIVE LOGITS
    님이
    0.07
    uns
    0.07
    _response
    0.07
    .Chain
    0.06
    =target
    0.06
    Jos
    0.06
    endars
    0.06
    नल
    0.06
    LENGTH
    0.06
     江
    0.06
    Act Density 0.001%

    No Known Activations