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

    Neuronpedia

    INDEX
    Explanations

    project management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ca
    -0.06
    -minus
    -0.06
     drawn
    -0.06
     vole
    -0.06
     Στα
    -0.06
    urring
    -0.06
    瀬
    -0.06
    调
    -0.06
    .di
    -0.06
    Composite
    -0.06
    POSITIVE LOGITS
    stylesheet
    0.07
     �
    0.07
    teenth
    0.06
    ]+"
    0.06
     DataManager
    0.06
    styl
    0.06
     barbecue
    0.06
     selectable
    0.06
     discard
    0.06
     reap
    0.06
    Act Density 0.031%

    No Known Activations