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

    Neuronpedia

    INDEX
    Explanations

    response

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decreased
    -0.07
    erno
    -0.07
    Swap
    -0.07
     competitiveness
    -0.07
    pectral
    -0.07
    _security
    -0.06
    558
    -0.06
    ева
    -0.06
    ується
    -0.06
    Descriptor
    -0.06
    POSITIVE LOGITS
     response
    0.07
     )"
    0.06
     PS
    0.06
    ******/↵
    0.06
    .reg
    0.06
     прож
    0.06
    .servers
    0.06
    .sam
    0.06
     GestureDetector
    0.06
    ",
↵
    0.06
    Act Density 0.015%

    No Known Activations