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

    Neuronpedia

    INDEX
    Explanations

    satisfies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    يان
    -0.06
     Repo
    -0.06
    DLL
    -0.06
     Marin
    -0.06
     amaç
    -0.06
     которого
    -0.05
    leasing
    -0.05
    greso
    -0.05
        		↵
    -0.05
    фров
    -0.05
    POSITIVE LOGITS
    _trajectory
    0.07
     completing
    0.07
     vit
    0.07
     onResponse
    0.07
    Ơ
    0.07
    _ACTIONS
    0.07
     incapac
    0.07
     Salary
    0.07
     EVT
    0.06
    -building
    0.06
    Act Density 0.000%

    No Known Activations