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

    Neuronpedia

    INDEX
    Explanations

    recommendations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.07
     NTN
    -0.07
     airstrikes
    -0.06
    :=
    -0.06
    _routes
    -0.06
     DACA
    -0.06
    _Header
    -0.05
    >Login
    -0.05
    Drag
    -0.05
    objectManager
    -0.05
    POSITIVE LOGITS
    ±n
    0.07
    .lon
    0.06
     société
    0.06
     strlen
    0.06
     spiele
    0.06
     Blu
    0.06
     sociedad
    0.06
    ケ
    0.06
    �다
    0.06
    郎
    0.06
    Act Density 0.266%

    No Known Activations