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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BindView
    -0.08
    ::::::::
    -0.08
    
    -0.08
     opport
    -0.07
    ᭣
    -0.07
    ifying
    -0.07
                    ↵                ↵
    -0.07
    ████
    -0.06
     desc
    -0.06
    images
    -0.06
    POSITIVE LOGITS
    (clock
    0.07
    "Some
    0.07
     SOC
    0.07
     Pact
    0.07
    -camera
    0.07
    laşma
    0.07
    .guard
    0.07
    公安局
    0.07
     SORT
    0.07
    .CREATE
    0.07
    Act Density 0.004%

    No Known Activations