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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Adv
    -0.07
     THINK
    -0.06
     prefab
    -0.06
     dime
    -0.06
    dre
    -0.06
    onica
    -0.06
    入れ
    -0.06
    -0.06
    dni
    -0.06
    fidf
    -0.06
    POSITIVE LOGITS
     Gobierno
    0.07
    /calendar
    0.07
    ução
    0.07
    _tests
    0.06
    Portal
    0.06
    zenie
    0.06
     watchers
    0.06
    efa
    0.06
    _alert
    0.06
    UILTIN
    0.06
    Act Density 0.032%

    No Known Activations