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

    Neuronpedia

    INDEX
    Explanations

    either

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.08
     акт
    -0.06
     crave
    -0.06
     cancel
    -0.06
     Haley
    -0.06
     ліс
    -0.06
    prar
    -0.06
    ibe
    -0.06
    уки
    -0.06
    й
    -0.06
    POSITIVE LOGITS
    received
    0.08
     natives
    0.07
     boot
    0.07
    getRequest
    0.07
    -resources
    0.07
     HACK
    0.07
    SQLException
    0.07
     Trade
    0.06
    certificate
    0.06
    atype
    0.06
    Act Density 0.001%

    No Known Activations