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

    Neuronpedia

    INDEX
    Explanations

    effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    星
    -0.07
    ESSAGE
    -0.06
     atr
    -0.06
    wf
    -0.06
    rob
    -0.06
    Knife
    -0.06
    RAND
    -0.06
    feas
    -0.06
    )tableView
    -0.06
     Andrew
    -0.06
    POSITIVE LOGITS
    Redirect
    0.07
    συ
    0.07
    ระ
    0.06
     networking
    0.06
     axial
    0.06
     normalized
    0.06
    ています
    0.06
    імі
    0.06
    تماع
    0.06
    ¶¶
    0.06
    Act Density 0.032%

    No Known Activations