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

    Neuronpedia

    INDEX
    Explanations

    salt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istros
    -0.07
    fect
    -0.07
    _mid
    -0.06
    .circular
    -0.06
     "")
    -0.06
    П
    -0.06
     detective
    -0.06
    ibu
    -0.06
     homeowners
    -0.06
     nicknamed
    -0.06
    POSITIVE LOGITS
     consumption
    0.07
    .setVisibility
    0.07
    _links
    0.06
     roční
    0.06
    ersion
    0.06
    .sendKeys
    0.06
     dolore
    0.06
    navbarDropdown
    0.06
     Decoder
    0.06
     connected
    0.06
    Act Density 0.002%

    No Known Activations