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

    Neuronpedia

    INDEX
    Explanations

    replacements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trustees
    -0.07
     hw
    -0.07
    認
    -0.06
    面
    -0.06
     devil
    -0.06
    681
    -0.06
     sklad
    -0.06
    川
    -0.06
    ceive
    -0.06
    ând
    -0.06
    POSITIVE LOGITS
    _Array
    0.07
    .Startup
    0.06
     전국
    0.06
    urnal
    0.06
     conditional
    0.06
     ("-
    0.06
     限
    0.06
    _CMP
    0.06
    _DEFINITION
    0.06
    metis
    0.06
    Act Density 0.026%

    No Known Activations