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

    Neuronpedia

    INDEX
    Explanations

    cornerstone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <context
    -0.06
     リ
    -0.06
    ворю
    -0.06
     ctrl
    -0.06
     Abstract
    -0.06
    Abstract
    -0.06
    scenes
    -0.06
    STATIC
    -0.06
     tradi
    -0.06
     potion
    -0.06
    POSITIVE LOGITS
     τις
    0.08
     cornerstone
    0.07
     Grants
    0.07
    นาง
    0.07
     Nexus
    0.07
     Moh
    0.06
    Reload
    0.06
    δρο
    0.06
    plet
    0.06
    .trim
    0.06
    Act Density 0.020%

    No Known Activations