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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    329
    -0.06
    seeing
    -0.06
     acquaint
    -0.06
    �
    -0.06
     dostan
    -0.06
     platforms
    -0.06
     зависит
    -0.06
     booming
    -0.06
    ียว
    -0.06
    show
    -0.06
    POSITIVE LOGITS
    AINER
    0.07
    گل
    0.06
    inha
    0.06
    (price
    0.06
    :any
    0.06
     |--
    0.06
     теб
    0.06
    ainer
    0.06
        ↵    ↵    ↵    ↵
    0.06
    ))->
    0.06
    Act Density 0.000%

    No Known Activations