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

    Neuronpedia

    INDEX
    Explanations

    Concentrations/measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Breitbart
    -0.07
    几百
    -0.06
     Establish
    -0.06
    pull
    -0.06
    addafi
    -0.06
    .Packet
    -0.06
    	NULL
    -0.06
    휑
    -0.06
    主线
    -0.06
    decrypt
    -0.06
    POSITIVE LOGITS
     cosas
    0.08
    Modifiers
    0.08
    _MetaData
    0.07
    =j
    0.07
    мещ
    0.07
     badass
    0.07
    +x
    0.07
    ὀ
    0.07
     &,
    0.07
    嵁
    0.07
    Act Density 0.009%

    No Known Activations