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

    Neuronpedia

    INDEX
    Explanations

    Intu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ly
    -0.65
    UT
    -0.60
    🏾
    -0.60
    RODUCTION
    -0.59
    manship
    -0.58
    tuar
    -0.56
    🏽
    -0.56
    🏿
    -0.56
    IntoConstraints
    -0.55
    ness
    -0.55
    POSITIVE LOGITS
     createSlice
    0.57
    Portail
    0.56
     Portail
    0.55
     depic
    0.52
     urma
    0.52
    endix
    0.50
     Audiodateien
    0.49
     trasladado
    0.49
    PRNewswire
    0.48
     metav
    0.47
    Act Density 0.035%

    No Known Activations